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

    Neuronpedia

    INDEX
    Explanations

    all prime numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tał
    0.50
    чною
    0.49
    제곱
    0.49
     Vestone
    0.47
    の実
    0.46
    сього
    0.45
     તમારી
    0.45
    ことなく
    0.45
     нож
    0.45
    轳
    0.45
    POSITIVE LOGITS
    y
    0.61
    u
    0.53
    $.
    0.53
    ims
    0.52
    ed
    0.49
    lee
    0.49
    b
    0.48
    z
    0.48
    ips
    0.48
    iron
    0.47
    Act Density 0.001%

    No Known Activations