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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric literals with a decimal point (i.e. floating-point constants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    RESS
    -0.07
    ادات
    -0.07
     pore
    -0.07
    .list
    -0.07
    了一
    -0.07
     číslo
    -0.07
    状況
    -0.07
    671
    -0.06
    •
    -0.06
     Wales
    -0.06
    POSITIVE LOGITS
    (filter
    0.06
    cstdio
    0.06
     configFile
    0.06
    :SetText
    0.06
    :y
    0.06
     tarafından
    0.05
     Osmanlı
    0.05
    Jobs
    0.05
    ٤
    0.05
     yüzyıl
    0.05
    Act Density 0.006%

    No Known Activations