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

    Neuronpedia

    INDEX
    Explanations

    references to social media account settings and elements related to web links

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

    Follows punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Again
    -0.72
     Together
    -0.63
     Then
    -0.60
     Because
    -0.57
     They
    -0.56
     According
    -0.55
     Their
    -0.55
    Again
    -0.55
    Saluti
    -0.54
     That
    -0.54
    POSITIVE LOGITS
     Se
    0.49
     Pentru
    0.48
     În
    0.45
    Se
    0.45
    Hozzáférés
    0.45
     Je
    0.43
     Una
    0.43
    Una
    0.43
    ChildScrollView
    0.43
     Este
    0.42
    Act Density 0.366%

    No Known Activations