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

    Neuronpedia

    INDEX
    Explanations

    code for file extraction

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (especially floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     horas
    -0.08
     الدولي
    -0.07
     vieille
    -0.07
    lot
    -0.06
    ownership
    -0.06
     dances
    -0.06
    lots
    -0.06
     visto
    -0.06
    _REFRESH
    -0.06
     Liga
    -0.06
    POSITIVE LOGITS
     UIImageView
    0.06
     Espresso
    0.06
     '''
    0.06
     Case
    0.06
    -await
    0.06
     hairstyle
    0.06
     Prospect
    0.06
    ливість
    0.05
    ="""
    0.05
     "../../
    0.05
    Act Density 0.009%

    No Known Activations