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

    Neuronpedia

    INDEX
    Explanations

    can adapt and generate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     constantemente
    0.84
     otomatik
    0.76
     automatically
    0.76
     zawsze
    0.75
     constantly
    0.75
     dostęp
    0.75
     vždy
    0.74
     continuamente
    0.74
     periodically
    0.74
     always
    0.72
    POSITIVE LOGITS
     complication
    0.88
     Manipulation
    0.86
    MatchType
    0.84
    idespread
    0.83
     variation
    0.80
     partake
    0.79
     manipulation
    0.78
     Teilnahme
    0.76
     complicating
    0.76
    LOTRE
    0.74
    Act Density 0.742%

    No Known Activations