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

    Neuronpedia

    INDEX
    Explanations

    non-english languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ild
    0.48
    ils
    0.47
    usk
    0.46
    lashes
    0.46
    els
    0.45
     disbursements
    0.44
    ifie
    0.44
    tape
    0.42
     sultry
    0.42
    ife
    0.42
    POSITIVE LOGITS
    ССР
    0.47
    요
    0.47
    ﻧ
    0.46
    الم
    0.45
    Ар
    0.43
    ர்
    0.42
    ن
    0.42
    Პ
    0.42
    Mé
    0.41
    初心者
    0.41
    Act Density 0.001%

    No Known Activations