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

    Neuronpedia

    INDEX
    Explanations

    consecutive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     problemat
    0.52
    Proble
    0.50
    proble
    0.50
     Isra
    0.49
    Israel
    0.46
    广西
    0.46
     Israël
    0.46
    崛
    0.44
     Израи
    0.44
     PROBLE
    0.43
    POSITIVE LOGITS
    0
    0.53
     wishes
    0.46
     ergonomic
    0.43
     uninterrupted
    0.43
     consecutive
    0.42
     adjusted
    0.42
    ຸນ
    0.42
     lifecycle
    0.41
     compatibility
    0.41
     permettent
    0.41
    Act Density 0.004%

    No Known Activations