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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron activates on the colon character “:” when used in slice/range expressions (e.g. list[start:stop], Python slicing).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     walk
    -0.07
    黑
    -0.07
    hledem
    -0.07
    :@"%
    -0.07
     bless
    -0.07
     objectively
    -0.06
    푸
    -0.06
     poco
    -0.06
     Mine
    -0.06
    PropertyParams
    -0.06
    POSITIVE LOGITS
    caret
    0.07
     Hentai
    0.06
     Modifier
    0.06
    ніч
    0.06
    mmas
    0.06
    strument
    0.06
    vb
    0.06
    \:
    0.06
     повинні
    0.06
    ních
    0.06
    Act Density 0.016%

    No Known Activations