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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially decimal numbers (e.g. percentages or floating‐point values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rear
    -0.07
    /span
    -0.06
     playwright
    -0.06
     accreditation
    -0.06
     accordance
    -0.06
     shortcomings
    -0.06
     paddingBottom
    -0.06
     JM
    -0.06
    ¢
    -0.06
    ический
    -0.06
    POSITIVE LOGITS
     záb
    0.07
    .Are
    0.06
    انو
    0.06
     lối
    0.06
    (cd
    0.06
    -fin
    0.06
    _DISK
    0.06
     су
    0.06
    +h
    0.06
     bekommen
    0.06
    Act Density 0.082%

    No Known Activations