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

    Neuronpedia

    INDEX
    Explanations

    foreign language or non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    profitLoss
    1.36
     reputed
    1.31
     അന്നനാള
    1.30
     geï
    1.28
     susceptibles
    1.28
     seizures
    1.26
    )%>%
    1.26
     cok
    1.25
     postulated
    1.24
     бі
    1.23
    POSITIVE LOGITS
    ות
    1.13
    нт
    1.04
    阈
    0.95
    arele
    0.94
     aire
    0.94
    ρία
    0.93
    ズニー
    0.92
    ర్ణ
    0.91
    Qué
    0.91
    ż
    0.91
    Act Density 0.000%

    No Known Activations