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

    Neuronpedia

    INDEX
    Explanations

    -bar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Bytes
    -0.07
    ()),
    -0.07
     converters
    -0.06
     poised
    -0.06
     Patterns
    -0.06
    378
    -0.06
    .general
    -0.06
    nego
    -0.06
     $"
    -0.06
    from
    -0.06
    POSITIVE LOGITS
    =document
    0.07
     Rally
    0.07
    urr
    0.06
     taky
    0.06
     victories
    0.06
    ımı
    0.06
     fark
    0.06
     constituents
    0.06
     Babe
    0.06
     Shame
    0.06
    Act Density 0.000%

    No Known Activations