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

    Neuronpedia

    INDEX
    Explanations

    / followed by writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ૂર્ણ
    0.80
     simplifié
    0.78
     teljesen
    0.77
    েলার
    0.74
    OGRAP
    0.74
     remedied
    0.74
     quinquina
    0.74
     quotid
    0.73
    市场的
    0.73
    在一个
    0.73
    POSITIVE LOGITS
    E
    1.13
    N
    0.90
    T
    0.89
    L
    0.89
    Z
    0.88
    K
    0.88
    J
    0.87
    D
    0.86
    S
    0.84
    F
    0.84
    Act Density 0.606%

    No Known Activations