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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs formatted as JSON objects

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

    structured data keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.48
    awtextra
    -0.47
    extAlignment
    -0.41
     confusión
    -0.40
     ascenso
    -0.39
    ьаж
    -0.39
     farlo
    -0.37
    éndolo
    -0.36
    styleable
    -0.36
    μβρίου
    -0.36
    POSITIVE LOGITS
    
    0.66
    GEBURTSDATUM
    0.55
    endpush
    0.45
    EDEFAULT
    0.44
    toplankton
    0.44
     []:
    0.43
    NameInMap
    0.42
    wapV
    0.41
    inander
    0.40
     برانيه
    0.40
    Act Density 2.165%

    No Known Activations