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

    Neuronpedia

    INDEX
    Explanations

    remaining time or characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    1.38
    ि
    1.20
    ु
    1.14
    스러
    1.14
     lever
    1.13
     aula
    1.11
    mol
    1.09
    ं
    1.07
     karna
    1.07
    ையம்
    1.06
    POSITIVE LOGITS
     frauds
    1.21
     dynasties
    1.13
    ான்
    1.11
     unbeaten
    1.08
     mockery
    1.08
    儕
    1.07
     бое
    1.07
     Crusade
    1.06
    ።
    1.04
     undefeated
    1.04
    Act Density 0.000%

    No Known Activations