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

    Neuronpedia

    INDEX
    Explanations

    demonstrate state, code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <strong>
    0.61
    ur
    0.61
    ut
    0.54
    Y
    0.53
    {
    0.52
    <0x0D>
    0.51
    W
    0.51
    pre
    0.49
    ran
    0.49
    entry
    0.49
    POSITIVE LOGITS
     utilizamos
    0.59
     utiliz
    0.55
     použití
    0.55
     dizajn
    0.54
     rotacao
    0.53
     použív
    0.52
     znači
    0.52
     زیرمه
    0.51
    ፨
    0.51
     stockno
    0.50
    Act Density 0.000%

    No Known Activations