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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indigenous
    -0.06
    ตก
    -0.06
    Jac
    -0.06
    ,max
    -0.06
     jos
    -0.06
     Historic
    -0.06
     meaningful
    -0.06
     county
    -0.06
     plateau
    -0.06
     king
    -0.06
    POSITIVE LOGITS
    党员
    0.07
    📅
    0.07
    jay
    0.07
    サラ
    0.07
    禔
    0.07
    /editor
    0.07
    bones
    0.06
    疐
    0.06
    WebHost
    0.06
    _COMMIT
    0.06
    Act Density 0.104%

    No Known Activations