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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of saving or exporting data—i.e. “save,” “savefig,” “dump,” etc.—in Python code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    855
    -0.06
     arousal
    -0.06
    _AFTER
    -0.06
    Scale
    -0.06
     мой
    -0.06
     Mara
    -0.06
     INLINE
    -0.06
     chuyên
    -0.06
     дет
    -0.06
    _MARK
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .Many
    0.07
    .Has
    0.07
    aidu
    0.07
    ança
    0.07
    ür
    0.06
    .Random
    0.06
    lett
    0.06
     Juventus
    0.06
    ToFront
    0.06
    Act Density 0.018%

    No Known Activations