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

    Neuronpedia

    INDEX
    Explanations

    defining a skeleton of an algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رم
    0.56
    рата
    0.55
    దు
    0.54
    لي
    0.54
    òng
    0.53
    ست
    0.53
    дже
    0.52
    كَ
    0.51
    فيق
    0.51
    يك
    0.51
    POSITIVE LOGITS
    tests
    0.52
    on
    0.50
     gallbladder
    0.49
    led
    0.49
    4
    0.48
    8
    0.47
    por
    0.47
    marker
    0.46
     steers
    0.45
    opia
    0.45
    Act Density 0.001%

    No Known Activations