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

    Neuronpedia

    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Custom
    -0.07
    .Offset
    -0.07
     God
    -0.07
    God
    -0.07
     CC
    -0.06
     jiného
    -0.06
    .Callback
    -0.06
    831
    -0.06
    _SIMPLE
    -0.06
     Star
    -0.06
    POSITIVE LOGITS
     시행
    0.07
    xf
    0.07
     γνω
    0.06
     listView
    0.06
     polov
    0.06
     Subtract
    0.06
     ().
    0.06
     значительно
    0.06
    습니다
    0.06
    √
    0.06
    Act Density 0.068%

    No Known Activations