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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     עצמי
    -0.07
    ㋴
    -0.07
    KeyUp
    -0.07
    ড
    -0.07
    _locale
    -0.06
    쭤
    -0.06
    シーン
    -0.06
    .environment
    -0.06
    tone
    -0.06
    POSITIVE LOGITS
    thermal
    0.07
    啥
    0.07
     kitt
    0.07
    قاء
    0.07
     Năm
    0.07
    isseur
    0.07
    (comment
    0.07
     fathers
    0.07
    瞿
    0.06
     priests
    0.06
    Act Density 0.016%

    No Known Activations