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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rallies
    -0.08
    _outline
    -0.08
    choose
    -0.08
    ंथ
    -0.08
     uitgang
    -0.08
     opdracht
    -0.07
    inion
    -0.07
    ಿಸಲಾಗಿದೆ
    -0.07
     cameo
    -0.07
    Faction
    -0.07
    POSITIVE LOGITS
    有什么
    0.09
     wondering
    0.09
     શું
    0.08
    Question
    0.08
    אש
    0.08
    What's
    0.07
    是否
    0.07
     question
    0.07
     dúvidas
    0.07
     Whats
    0.07
    Act Density 0.055%

    No Known Activations