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

    Neuronpedia

    INDEX
    Explanations

    file extensions typically associated with images and HTML documents

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

    file types and data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.82
     ſei
    -0.79
    iſen
    -0.77
     ModelExpression
    -0.76
    ſſung
    -0.76
     betweenstory
    -0.76
     houſe
    -0.75
    ########.
    -0.75
     ſeine
    -0.74
     beſte
    -0.74
    POSITIVE LOGITS
    .
    0.53
     with
    0.46
     now
    0.43
    ,
    0.40
     With
    0.40
     for
    0.38
     where
    0.37
     is
    0.37
     when
    0.36
    With
    0.36
    Act Density 0.015%

    No Known Activations