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

    Neuronpedia

    INDEX
    Explanations

    National, Time, Loss, Game, David

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sure
    1.22
     candid
    1.15
    ti
    1.07
    do
    1.03
    s
    0.95
    the
    0.95
    sprite
    0.94
    String
    0.93
    snapshot
    0.93
    eyed
    0.92
    POSITIVE LOGITS
    ٹن
    1.46
    𝗠
    1.41
    upné
    1.37
     Национа
    1.35
    ícul
    1.32
    ɴ
    1.31
    entive
    1.30
     attraction
    1.26
     електро
    1.26
     Фі
    1.26
    Act Density 0.001%

    No Known Activations