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

    Neuronpedia

    INDEX
    Explanations

    programming/technical problems

    np_max-act · gemini-2.0-flash

    technical jargon related to software development and API usage.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on numeric or numeric‐like tokens (e.g., literal numbers, decimal values, error codes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    機能
    -0.07
    Aliases
    -0.07
    _cd
    -0.06
    ﾞ
    -0.06
     externally
    -0.06
     Manager
    -0.06
     IIC
    -0.06
    劳
    -0.06
     данных
    -0.06
    سام
    -0.06
    POSITIVE LOGITS
    に向
    0.07
     Basel
    0.07
     pes
    0.06
     transpose
    0.06
     Dirk
    0.06
     ให
    0.06
    engage
    0.06
     peril
    0.05
    ัญญ
    0.05
    ètres
    0.05
    Act Density 0.119%

    No Known Activations