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

    Neuronpedia

    INDEX
    Explanations

    categories or classifications in a text

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

    Category:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.56
    httphttps
    -0.49
     autorytatywna
    -0.47
     Wikimedijinoj
    -0.46
    AutoScaleMode
    -0.43
     Wiktionnaire
    -0.40
     Schließlich
    -0.40
    pdev
    -0.39
     pytest
    -0.39
    amos
    -0.39
    POSITIVE LOGITS
    enumii
    0.45
     kaarangay
    0.39
    CHAFT
    0.38
    delwed
    0.37
     vision
    0.37
     Мат
    0.36
    HasOne
    0.36
    Климаты
    0.36
     bougies
    0.35
     lights
    0.35
    Act Density 0.003%

    No Known Activations