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

    Neuronpedia

    INDEX
    Explanations

    warnings and manuals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生き
    -0.08
    DoubleClick
    -0.07
     winning
    -0.07
    _Invoke
    -0.06
    خرو
    -0.06
     Phill
    -0.06
     ning
    -0.06
    列入
    -0.06
    롵
    -0.06
     vw
    -0.06
    POSITIVE LOGITS
    sha
    0.06
    flags
    0.06
    AZ
    0.06
     based
    0.06
     quant
    0.06
    本基金
    0.06
    热线
    0.06
    过剩
    0.06
    fil
    0.06
    atches
    0.06
    Act Density 0.029%

    No Known Activations