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

    Neuronpedia

    INDEX
    Explanations

    periods and special characters typically used in punctuation

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

    end of sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
     semula
    -0.50
     kerjasama
    -0.47
     chiaramente
    -0.47
     adicionais
    -0.47
     merak
    -0.47
     essenziale
    -0.46
     malheureux
    -0.46
     nødven
    -0.46
     conosciuto
    -0.46
    POSITIVE LOGITS
    +#+#
    0.48
     purpure
    0.44
    GEBURTS
    0.43
    URLException
    0.42
     Pham
    0.42
    Filmografie
    0.41
    bootstrapcdn
    0.40
    rschein
    0.40
     CommonModule
    0.39
     TestBed
    0.38
    Act Density 0.453%

    No Known Activations