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

    Neuronpedia

    INDEX
    Explanations

    statements/sentence beginnings

    np_max-act · gemini-2.0-flash

    This neuron responds to common function words and punctuation (e.g., “the,” “and,” “not,” commas, periods).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /games
    -0.07
    _STENCIL
    -0.07
    _strength
    -0.07
     digits
    -0.06
     tête
    -0.06
    dess
    -0.06
     شناخته
    -0.06
    ूस
    -0.06
    apses
    -0.06
     realizar
    -0.06
    POSITIVE LOGITS
    Feb
    0.07
     REFER
    0.06
     Punjab
    0.06
    Invoice
    0.06
     آنلاین
    0.06
    358
    0.06
    备份
    0.06
     putt
    0.06
    Germany
    0.06
     forward
    0.06
    Act Density 0.015%

    No Known Activations