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

    Neuronpedia

    INDEX
    Explanations

    accumulate

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens representing fractional values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     acı
    -0.07
     peru
    -0.06
     AssemblyDescription
    -0.06
     Alta
    -0.06
     tre
    -0.06
    Nobody
    -0.06
    ﻨ
    -0.06
    GLenum
    -0.06
    _ENUM
    -0.06
    ése
    -0.06
    POSITIVE LOGITS
    IFY
    0.06
    dej
    0.06
    lander
    0.06
    Sphere
    0.06
    cular
    0.06
     MVC
    0.06
    cac
    0.06
    lek
    0.06
    ，這
    0.06
    ^K
    0.06
    Act Density 0.009%

    No Known Activations