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

    Neuronpedia

    INDEX
    Explanations

    . means what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    1.08
    te
    1.05
    m
    1.04
     Quels
    1.02
     Возможно
    0.99
    n
    0.98
     Staaten
    0.95
     Хотя
    0.95
     Systeme
    0.94
     конце
    0.93
    POSITIVE LOGITS
     basics
    0.77
     skips
    0.76
     obliter
    0.75
     textures
    0.74
     powders
    0.73
     disinfecting
    0.72
     predecessors
    0.72
     stuffs
    0.72
     remainder
    0.70
     embryo
    0.70
    Act Density 0.001%

    No Known Activations