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

    Neuronpedia

    INDEX
    Explanations

    special characters related to exclamation and emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expression markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éez
    -0.64
    outre
    -0.60
     Numerade
    -0.58
    tagHelperRunner
    -0.58
    nze
    -0.57
    KURZBESCHREIBUNG
    -0.56
    etap
    -0.56
     تان
    -0.56
     Dosage
    -0.56
    pyplot
    -0.55
    POSITIVE LOGITS
     अ
    1.66
    अ
    1.27
     અ
    1.09
     ਅ
    1.00
     অ
    0.92
    অ
    0.85
    અ
    0.84
     అ
    0.81
     ಅ
    0.81
     അ
    0.74
    Act Density 0.010%

    No Known Activations