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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate addition or accumulation of information

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

    introducing additional information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.65
    verwijspagina
    -0.59
     незавершена
    -0.56
    RTEE
    -0.54
     LoginForm
    -0.54
    Xna
    -0.52
    UserScript
    -0.52
    WireFormatLite
    -0.52
    Diweddarwch
    -0.52
    فایل‌لار
    -0.52
    POSITIVE LOGITS
     addition
    0.77
    Additionally
    0.72
     además
    0.72
     Additionally
    0.68
     além
    0.68
     additionally
    0.68
     inoltre
    0.64
    Furthermore
    0.64
    кож
    0.61
    Inoltre
    0.60
    Act Density 0.147%

    No Known Activations