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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in textual data, often indicating sections with repetition or formatting

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

    Woman, return, if, AC, Total

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.78
    ThroughAttribute
    -0.57
    sizeCache
    -0.50
     Comprometido
    -0.50
     anún
    -0.50
    хьтан
    -0.49
     étranger
    -0.47
     avoient
    -0.47
    UnitTesting
    -0.47
     Préférences
    -0.47
    POSITIVE LOGITS
    pcm
    0.42
     sart
    0.41
    펴
    0.40
    RefNanny
    0.39
     ze
    0.39
     dro
    0.38
     bif
    0.38
     Puk
    0.38
    клопе
    0.38
     rac
    0.38
    Act Density 0.052%

    No Known Activations