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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    This neuron fires on isolated numeric or abbreviated tokens—e.g., standalone numbers (like “one”) and short all-caps abbreviations (like “U.S.”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _cc
    -0.07
     flourish
    -0.07
     Brace
    -0.06
     майбут
    -0.06
     west
    -0.06
    uilt
    -0.06
     Mesh
    -0.06
     revolver
    -0.06
     ample
    -0.06
     vehicles
    -0.06
    POSITIVE LOGITS
    _Meta
    0.07
    OnClickListener
    0.07
    ابي
    0.07
     člen
    0.06
    .website
    0.06
    spo
    0.06
    Binding
    0.06
    _SEGMENT
    0.06
    assertTrue
    0.06
    	Label
    0.06
    Act Density 0.000%

    No Known Activations