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

    Neuronpedia

    INDEX
    Explanations

    cadena de documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ୫
    1.06
     treatise
    0.98
    を実現
    0.98
     seclusion
    0.98
     rejuvenate
    0.97
    एफसी
    0.97
     cohomology
    0.97
     solidaridad
    0.96
     Temos
    0.95
     fémin
    0.94
    POSITIVE LOGITS
     Pr
    0.83
    list
    0.80
     Pol
    0.73
    PHEN
    0.73
    ness
    0.72
     P
    0.71
    DS
    0.70
     Pe
    0.69
    DO
    0.69
    leep
    0.69
    Act Density 0.000%

    No Known Activations