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

    Neuronpedia

    INDEX
    Explanations

    code keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inept
    0.49
    то
    0.48
     ਇੱਕ
    0.47
    𝚟
    0.47
     pedestrian
    0.46
    toires
    0.46
    ផ្ត
    0.46
     indulgent
    0.45
     excuses
    0.44
    ニャ
    0.44
    POSITIVE LOGITS
    Pat
    0.45
    0.45
    Days
    0.43
     yıll
    0.43
    FOLLOW
    0.42
    iß
    0.41
    getBoolean
    0.41
    Parse
    0.41
    ابی
    0.40
    Being
    0.40
    Act Density 0.008%

    No Known Activations