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

    Neuronpedia

    INDEX
    Explanations

    reality every moment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chandise
    0.46
    レスレット
    0.41
     vergleich
    0.41
     Obligations
    0.39
     bille
    0.39
    ManagerPortal
    0.38
     palette
    0.38
    朋友們
    0.38
    bí
    0.38
    驟
    0.38
    POSITIVE LOGITS
    IntVar
    0.41
    டல்
    0.37
    optimizer
    0.37
     chciał
    0.36
     Warsaw
    0.35
    ဆုံး
    0.35
    วก
    0.35
     मसा
    0.35
    hd
    0.35
    Burg
    0.34
    Act Density 0.000%

    No Known Activations