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

    Neuronpedia

    INDEX
    Explanations

    descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ikke
    1.02
     entretenimiento
    1.01
     jogadores
    1.00
     preocupaciones
    0.97
     notwend
    0.97
    Nicht
    0.93
     साथ
    0.93
     escenarios
    0.93
     potere
    0.92
     जरूरी
    0.91
    POSITIVE LOGITS
     שב
    0.87
    cks
    0.82
     &
    0.78
     ck
    0.75
    ²
    0.74
     ≤
    0.74
    ³.
    0.74
    ana
    0.73
    rising
    0.71
    ess
    0.71
    Act Density 0.557%

    No Known Activations