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

    Neuronpedia

    INDEX
    Explanations

    reporting and complaints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।’
    0.74
    ।”
    0.69
    。“
    0.65
    。
    0.65
    ।'
    0.64
    。\
    0.63
    ции
    0.62
    கிறது
    0.61
    .}$
    0.60
    ।
    0.60
    POSITIVE LOGITS
    de
    0.86
    i
    0.78
    V
    0.73
    at
    0.70
    C
    0.70
    n
    0.69
    f
    0.68
    c
    0.68
    P
    0.68
     Complaint
    0.66
    Act Density 0.167%

    No Known Activations