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
    _domain
    -0.07
     ジ
    -0.06
    ={↵
    -0.06
    _HEIGHT
    -0.06
     getState
    -0.06
    /comment
    -0.06
    	for
    -0.06
    Story
    -0.06
    customer
    -0.06
    .Fields
    -0.06
    POSITIVE LOGITS
     облас
    0.08
    ينا
    0.06
    YG
    0.06
    GBT
    0.06
     Krak
    0.06
    umat
    0.06
    UInt
    0.06
     PD
    0.06
    prove
    0.06
     Conduct
    0.06
    Act Density 0.072%

    No Known Activations