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

    Neuronpedia

    INDEX
    Explanations

    ita

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MET
    -0.07
    とう
    -0.07
    iners
    -0.06
    .accuracy
    -0.06
    Currency
    -0.06
    elapsed
    -0.06
    ียญ
    -0.06
    .Minimum
    -0.06
    _steps
    -0.06
     susceptibility
    -0.06
    POSITIVE LOGITS
    ̣
    0.06
     complaining
    0.06
    들의
    0.06
    ��
    0.06
     joined
    0.06
     yaml
    0.06
    959
    0.06
     LX
    0.06
     лица
    0.06
     사실
    0.06
    Act Density 0.018%

    No Known Activations