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

    Neuronpedia

    INDEX
    Explanations

    My Safety Guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    typeof
    0.39
    affected
    0.38
    unnumbered
    0.38
    rawn
    0.37
    rights
    0.37
     values
    0.37
    right
    0.36
    tab
    0.36
    param
    0.35
    oms
    0.35
    POSITIVE LOGITS
     konfigur
    0.51
    숴
    0.43
     heresy
    0.43
     legions
    0.43
    ロボ
    0.42
     installé
    0.42
     demonic
    0.41
     Datenbank
    0.40
     sistem
    0.40
    犟
    0.40
    Act Density 0.422%

    No Known Activations