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

    Neuronpedia

    INDEX
    Explanations

    Code and numerical data

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (especially floating-point or decimal number tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Disp
    -0.07
     livro
    -0.07
     nrows
    -0.07
     Era
    -0.07
    .final
    -0.06
     situ
    -0.06
     Donetsk
    -0.06
    _br
    -0.06
     politics
    -0.06
     Am
    -0.06
    POSITIVE LOGITS
     Seeder
    0.07
    >O
    0.06
     zza
    0.06
    >
    0.06
     đen
    0.06
     способом
    0.06
    ě
    0.06
    Er
    0.06
     رم
    0.06
    uge
    0.06
    Act Density 0.019%

    No Known Activations