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

    Neuronpedia

    INDEX
    Explanations

    endearing characters and future situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อบคุณ
    0.47
    ท
    0.45
    इ
    0.41
    то
    0.41
    ро
    0.39
    ซ
    0.39
    Mang
    0.39
    д
    0.38
    icism
    0.38
    드
    0.38
    POSITIVE LOGITS
     straightforward
    0.45
     listo
    0.44
     irrespective
    0.40
     liquors
    0.39
     minuti
    0.39
    banam
    0.39
     Jeanne
    0.38
     दैट
    0.38
     IUnary
    0.38
     Ferté
    0.37
    Act Density 0.000%

    No Known Activations