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

    Neuronpedia

    INDEX
    Explanations

    code/special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    APPLE
    -0.07
     envelopes
    -0.07
     Bowen
    -0.07
     composers
    -0.06
     полити
    -0.06
    行动
    -0.06
     VO
    -0.06
     ethnic
    -0.06
    accom
    -0.06
     Foley
    -0.06
    POSITIVE LOGITS
    ;");↵
    0.07
     riot
    0.06
     Trailer
    0.06
    _block
    0.06
    ]);↵↵
    0.06
     ));↵
    0.06
     Sci
    0.06
    .Comp
    0.06
    DefaultCellStyle
    0.06
     reset
    0.06
    Act Density 0.065%

    No Known Activations