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

    Neuronpedia

    INDEX
    Explanations

    calculations or programming

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point number tokens (numeric values containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    مز
    -0.07
    Để
    -0.06
     dar
    -0.06
     věn
    -0.06
     Worksheet
    -0.06
     trustee
    -0.06
    Esc
    -0.06
    미
    -0.06
     backgroundImage
    -0.06
    火
    -0.06
    POSITIVE LOGITS
    /down
    0.07
    廣
    0.07
     unions
    0.06
    programs
    0.06
    warehouse
    0.06
    ذكر
    0.06
    CONF
    0.06
    ieties
    0.06
     جمع
    0.06
    атель
    0.06
    Act Density 0.113%

    No Known Activations