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

    Neuronpedia

    INDEX
    Explanations

    devices activated or on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     встреча
    0.81
     исче
    0.78
     difíciles
    0.77
     terbentuk
    0.76
     کیسے
    0.76
    可以用
    0.76
     difícil
    0.75
     тяжело
    0.75
     лучших
    0.74
    iformis
    0.74
    POSITIVE LOGITS
     aktiviert
    1.48
     activated
    1.44
     active
    1.43
     activate
    1.37
     togg
    1.36
     activation
    1.32
     toggle
    1.30
     Active
    1.30
     режим
    1.30
     aktivieren
    1.25
    Act Density 0.293%

    No Known Activations