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

    Neuronpedia

    INDEX
    Explanations

    database types and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    циона
    0.85
     Crusaders
    0.80
     LocalDateTime
    0.79
    wana
    0.79
     Muay
    0.78
     Cyclone
    0.76
     ofApp
    0.76
     Obrigado
    0.75
    Twe
    0.74
     Twe
    0.74
    POSITIVE LOGITS
     dom
    0.74
     tag
    0.72
     c
    0.68
    jst
    0.67
     general
    0.66
    ಿಸ
    0.66
    หย
    0.65
     element
    0.64
     aspect
    0.64
    tag
    0.64
    Act Density 0.002%

    No Known Activations