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

    Neuronpedia

    INDEX
    Explanations

    variation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hay
    -0.07
    (weight
    -0.07
    メ
    -0.07
    能够
    -0.06
    ,lat
    -0.06
     комнат
    -0.06
    我
    -0.06
     empath
    -0.06
     mesaj
    -0.06
    ुआत
    -0.06
    POSITIVE LOGITS
    getTitle
    0.07
    販
    0.06
     ー
    0.06
    AY
    0.06
     hö
    0.06
    辅
    0.06
     AMP
    0.06
    iper
    0.06
    EXTERN
    0.06
    teborg
    0.06
    Act Density 0.047%

    No Known Activations