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

    Neuronpedia

    INDEX
    Explanations

    on phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gegenwart
    0.37
    बत
    0.33
    凛
    0.33
    ####
    0.33
    gameObject
    0.33
    ♠
    0.33
    感動
    0.32
     nonempty
    0.30
    Core
    0.30
    ++){
    0.30
    POSITIVE LOGITS
     liste
    0.48
     lijst
    0.45
     list
    0.44
     lists
    0.44
     لیست
    0.44
     온
    0.43
     lista
    0.41
     alerts
    0.39
     yük
    0.38
     Liste
    0.38
    Act Density 0.039%

    No Known Activations