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

    Neuronpedia

    INDEX
    Explanations

    code block syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     všet
    0.95
    м
    0.93
     χρησιμοποι
    0.89
     residuos
    0.87
     funziona
    0.87
     biologiques
    0.87
    腧
    0.87
     peralatan
    0.87
     biologique
    0.86
     każ
    0.86
    POSITIVE LOGITS
    da
    1.06
    ra
    1.03
    type
    0.99
    k
    0.95
    te
    0.91
    D
    0.88
    ss
    0.87
     Influence
    0.86
    T
    0.85
    tone
    0.85
    Act Density 0.000%

    No Known Activations