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

    Neuronpedia

    INDEX
    Explanations

    giving credit or credits required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.28
    !
    1.27
     was
    1.15
    ้
    1.13
    1.09
    ।
    1.01
    ons
    0.98
    。
    0.97
    ص
    0.96
    ுகிறது
    0.93
    POSITIVE LOGITS
    n
    1.19
    У
    0.98
    juje
    0.96
     poderia
    0.91
    m
    0.90
    to
    0.90
    JsonPart
    0.88
    ೋಜನ
    0.88
     crédito
    0.87
    Α
    0.86
    Act Density 0.010%

    No Known Activations