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

    Neuronpedia

    INDEX
    Explanations

    it/MIT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Casino
    -0.07
     zařízení
    -0.07
     pathways
    -0.07
     nuova
    -0.07
     Yellow
    -0.07
     Taliban
    -0.06
     şarkı
    -0.06
    ียด
    -0.06
     Agriculture
    -0.06
     valeur
    -0.06
    POSITIVE LOGITS
    (op
    0.08
    +h
    0.07
    関係
    0.07
    mit
    0.07
    Mate
    0.07
    INCT
    0.07
    िट
    0.06
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
    _CMP
    0.06
     mitt
    0.06
    Act Density 0.004%

    No Known Activations