Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases in various languages, particularly focusing on personal pronouns and other related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Capital letter followed by another letter

    np_acts-logits-general · gemini-2.0-flash

    Ebraheim, Obstructive, concluded, Six Million

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.65
     فريبيس
    -0.63
     Picchu
    -0.63
    quiao
    -0.61
    Autoritní
    -0.60
    ...".
    -0.59
    áctenos
    -0.59
    XmlAccessType
    -0.57
    jgl
    -0.57
    ⓘ
    -0.55
    POSITIVE LOGITS
     مشين
    0.69
    fortun
    0.63
     entanto
    0.60
    Besides
    0.59
     besides
    0.59
     reason
    0.57
    theless
    0.57
     voilà
    0.56
     sure
    0.56
    etheless
    0.55
    Act Density 0.121%

    No Known Activations