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

    Neuronpedia

    INDEX
    Explanations

    coding methods/functions

    np_max-act · gemini-2.0-flash

    This neuron activates on code‐markup tokens (e.g. backtick fences, code block delimiters, and special code‐related markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tensor
    -0.07
     řízení
    -0.07
    gtk
    -0.07
     Silk
    -0.07
    šker
    -0.06
    \
↵
    -0.06
    ments
    -0.06
     contamination
    -0.06
     spoon
    -0.06
    ITE
    -0.06
    POSITIVE LOGITS
     бор
    0.07
     plead
    0.06
     putas
    0.06
    .WriteByte
    0.06
    摆
    0.06
     patří
    0.06
     unfamiliar
    0.06
     定
    0.06
     �
    0.06
     Stadium
    0.06
    Act Density 0.023%

    No Known Activations