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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing decimal or fractional values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ed
    -0.07
     Chain
    -0.07
     stimulated
    -0.06
     Sexy
    -0.06
     HER
    -0.06
     طبي
    -0.06
     escorted
    -0.06
     vintage
    -0.06
    +c
    -0.06
    ater
    -0.06
    POSITIVE LOGITS
    _direct
    0.07
    preferred
    0.06
    _subject
    0.06
    dict
    0.06
    Stage
    0.06
     Protestant
    0.06
    �
    0.06
    าศ
    0.06
     тяж
    0.06
    _age
    0.06
    Act Density 0.785%

    No Known Activations