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

    Neuronpedia

    INDEX
    Explanations

    positive assessment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inhabitants
    -0.06
     Wars
    -0.06
    aled
    -0.06
    iyi
    -0.06
    jedn
    -0.06
    뮤
    -0.06
    _mtx
    -0.06
     Heaven
    -0.06
     Lives
    -0.06
     Kenn
    -0.06
    POSITIVE LOGITS
    .Exception
    0.07
    ティ
    0.07
    oulouse
    0.07
    _IF
    0.06
    subtract
    0.06
    .");
    0.06
    'int
    0.06
     RPM
    0.06
     fa
    0.06
     merak
    0.06
    Act Density 0.029%

    No Known Activations