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

    Neuronpedia

    INDEX
    Explanations

    take, pass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indexOf
    -0.07
    .is
    -0.07
    лятор
    -0.06
     Processor
    -0.06
    avors
    -0.06
     questi
    -0.06
    _rt
    -0.06
     cmb
    -0.06
     endpoint
    -0.06
     letto
    -0.06
    POSITIVE LOGITS
    ологичес
    0.07
    成立
    0.06
     approaches
    0.06
    ительное
    0.06
    щими
    0.06
     bund
    0.06
     zah
    0.06
    eful
    0.06
     inval
    0.06
     hotline
    0.06
    Act Density 0.003%

    No Known Activations