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

    Neuronpedia

    INDEX
    Explanations

    smart fridgecouplesun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adverse
    0.47
     Avalanche
    0.46
     Taban
    0.45
     Shear
    0.44
     Magnificent
    0.44
    Ava
    0.43
     Cornell
    0.43
     Stair
    0.43
     Seç
    0.43
     Astrophysics
    0.43
    POSITIVE LOGITS
     gameObject
    0.48
    心配
    0.47
    ノ
    0.47
    explique
    0.46
    maßen
    0.44
     있지만
    0.44
    ]，
    0.43
    IN
    0.43
    します
    0.42
     ゲーム
    0.42
    Act Density 0.002%

    No Known Activations