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

    Neuronpedia

    INDEX
    Explanations

    Tesla units, challenging gameplay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UNICATIONS
    0.53
    Area
    0.51
    warn
    0.49
     كانوا
    0.49
    ClN
    0.49
    hrs
    0.48
     제거
    0.48
     ଜ
    0.48
    obs
    0.48
    AY
    0.47
    POSITIVE LOGITS
     Freude
    0.52
    积极
    0.46
     Vorstellung
    0.46
     Liebe
    0.45
     Questo
    0.45
    营养
    0.43
     ৭০
    0.42
     amely
    0.42
     plaisir
    0.41
    ன்ற
    0.41
    Act Density 0.003%

    No Known Activations