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

    Neuronpedia

    INDEX
    Explanations

    technical topics

    np_max-act · gemini-2.0-flash

    This neuron spot­lights numeric tokens containing decimal points (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
     activists
    -0.06
    _ele
    -0.06
    RetVal
    -0.06
     yazar
    -0.06
     işç
    -0.06
     als
    -0.06
    ělí
    -0.06
     Roman
    -0.06
    自拍
    -0.06
    POSITIVE LOGITS
    ,line
    0.08
     IDS
    0.07
     carrot
    0.06
     seasoned
    0.06
     ruta
    0.06
    าม
    0.06
     otra
    0.06
    ensure
    0.06
    ived
    0.06
     ipairs
    0.06
    Act Density 0.000%

    No Known Activations