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

    Neuronpedia

    INDEX
    Explanations

    Gemma AI assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gem
    0.45
    Kate
    0.41
    cy
    0.38
     Meadow
    0.38
     folk
    0.38
    Gem
    0.38
    folk
    0.37
     Kate
    0.37
    ガス
    0.37
     Gis
    0.37
    POSITIVE LOGITS
    ත්තේ
    0.42
    observatoire
    0.41
     विन
    0.37
    Technische
    0.37
    电视台
    0.37
     violência
    0.37
     rien
    0.36
     Trabalho
    0.36
    ivité
    0.36
     जिल्ह्यातील
    0.36
    Act Density 0.012%

    No Known Activations