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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flare
    -0.06
    -have
    -0.06
    Australia
    -0.06
    voř
    -0.06
     Taj
    -0.06
    _lead
    -0.06
    -letter
    -0.06
    値
    -0.06
    Have
    -0.06
    規
    -0.06
    POSITIVE LOGITS
     muschi
    0.07
     McCorm
    0.07
    -components
    0.06
    .Authentication
    0.06
    .PI
    0.06
    .RowIndex
    0.06
     ebony
    0.06
     akşam
    0.06
    Trans
    0.06
     OMX
    0.06
    Act Density 0.005%

    No Known Activations