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

    Neuronpedia

    INDEX
    Explanations

    activities/happenings

    np_max-act · gemini-2.0-flash

    the neuron fires on tokens representing floating-point numbers (decimal numerals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    γχ
    -0.06
    ly
    -0.06
    dü
    -0.06
    .cover
    -0.06
     Documentary
    -0.06
    Clip
    -0.06
     gibi
    -0.06
    .codec
    -0.06
    .rx
    -0.06
    Ensure
    -0.06
    POSITIVE LOGITS
     edeb
    0.07
    birds
    0.06
    ників
    0.06
    arma
    0.06
    .tipo
    0.06
     треба
    0.06
     puede
    0.06
    tape
    0.06
     nod
    0.06
     etraf
    0.06
    Act Density 0.052%

    No Known Activations