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

    Neuronpedia

    INDEX
    Explanations

    key phrases associated with questions and uncertainty

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

    starting phrase or sentence at beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.65
     asesinado
    -0.46
     consecuencia
    -0.45
     disambiguazione
    -0.42
    msgTypes
    -0.42
    帖最后由
    -0.41
    省市镇
    -0.41
    izaron
    -0.40
     będę
    -0.40
     Italijanski
    -0.40
    POSITIVE LOGITS
     فريبيس
    0.57
     كومونز
    0.57
     sneeze
    0.48
     blit
    0.47
     VIDEOTAPE
    0.46
     تانيه
    0.45
     Barcel
    0.44
     Initialized
    0.44
     Aussie
    0.43
    üssel
    0.43
    Act Density 0.034%

    No Known Activations