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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Username
    -0.07
    Agregar
    -0.07
    HttpClient
    -0.07
     Turnbull
    -0.06
    acement
    -0.06
     نشده
    -0.06
    Cube
    -0.06
    舍
    -0.06
     EXAMPLE
    -0.06
    "N
    -0.06
    POSITIVE LOGITS
     becoming
    0.07
    يش
    0.07
    /storage
    0.07
    _TIMER
    0.07
     før
    0.06
     FontStyle
    0.06
    Msg
    0.06
     useHistory
    0.06
     cin
    0.06
     starting
    0.06
    Act Density 0.000%

    No Known Activations