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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doch
    -0.07
     unsub
    -0.07
    洼
    -0.07
     setSelected
    -0.07
    确诊病例
    -0.07
    パパ
    -0.07
    .newInstance
    -0.06
     Citizen
    -0.06
    新华网
    -0.06
     sudden
    -0.06
    POSITIVE LOGITS
    гранич
    0.07
     lineWidth
    0.07
    -but
    0.06
    ?("
    0.06
    샙
    0.06
     jel
    0.06
     המ
    0.06
    .pen
    0.06
    )'),
    0.06
    WITHOUT
    0.06
    Act Density 0.004%

    No Known Activations