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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are floating‐point numbers (i.e. numeric literals containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     вза
    -0.06
     cannabinoids
    -0.06
     Kinh
    -0.06
     lunches
    -0.06
     преж
    -0.06
     strokeWidth
    -0.06
    란
    -0.06
    독
    -0.06
     JSGlobal
    -0.06
     KE
    -0.06
    POSITIVE LOGITS
    ospital
    0.07
    ...");↵↵
    0.07
    _nome
    0.06
    lescope
    0.06
     nossa
    0.06
    UDGE
    0.06
     Newly
    0.06
     patri
    0.06
     mı
    0.06
    ′
    0.06
    Act Density 0.025%

    No Known Activations