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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric measurement tokens—especially floating‐point numbers or numbers with decimal fractions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Schwarz
    -0.07
    768
    -0.07
    /W
    -0.07
     [{↵
    -0.07
     gü
    -0.06
     surviv
    -0.06
    _WINDOW
    -0.06
     Coordinate
    -0.06
    Color
    -0.06
    .raise
    -0.06
    POSITIVE LOGITS
    ней
    0.07
     as
    0.07
    ство
    0.06
     estão
    0.06
     Sta
    0.06
    0.06
    nombre
    0.06
    VE
    0.06
    _salt
    0.06
     outras
    0.06
    Act Density 0.067%

    No Known Activations