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

    Neuronpedia

    INDEX
    Explanations

    store pickup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.70
    માં
    0.62
    as
    0.61
    ución
    0.61
     сю
    0.58
     जल्दी
    0.57
    コレート
    0.57
     здесь
    0.56
    ชนะ
    0.56
     शीर्ष
    0.56
    POSITIVE LOGITS
    K
    0.91
    C
    0.72
    L
    0.71
    N
    0.70
    U
    0.68
    B
    0.67
    P
    0.66
    Y
    0.64
    G
    0.64
    F
    0.63
    Act Density 0.000%

    No Known Activations