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

    Neuronpedia

    INDEX
    Explanations

    subscripted variables

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric literals with decimal points (i.e. floating-point numbers) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Iron
    -0.07
    paration
    -0.06
    wh
    -0.06
    -phone
    -0.06
     HK
    -0.06
    Apparently
    -0.06
    -player
    -0.06
     zeigen
    -0.06
    _SHORT
    -0.06
    shown
    -0.06
    POSITIVE LOGITS
     Sole
    0.07
     Crom
    0.07
     �
    0.07
     Fuk
    0.06
    :update
    0.06
    vinfos
    0.06
    -close
    0.06
    นก
    0.06
    etleri
    0.06
    (sum
    0.06
    Act Density 0.007%

    No Known Activations