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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron is triggered by tokens representing decimal fractions (i.e. numeric strings with a “.”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     puta
    -0.06
     промислов
    -0.06
     liters
    -0.06
     견
    -0.06
     extrad
    -0.06
     ハ
    -0.06
     Bard
    -0.06
    /documentation
    -0.05
    EINVAL
    -0.05
    jection
    -0.05
    POSITIVE LOGITS
     Fig
    0.07
     unsigned
    0.07
    .Right
    0.07
    Fig
    0.07
     hitting
    0.06
    …
    0.06
    …”
    0.06
     Allies
    0.06
     lifetime
    0.06
    stood
    0.06
    Act Density 0.232%

    No Known Activations