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

    Neuronpedia

    INDEX
    Explanations

    math, algorithms, tactics, summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +
    0.60
    س
    0.55
    T
    0.52
    0.50
    Version
    0.49
    IN
    0.47
    .
    0.46
    R
    0.46
    H
    0.46
    _
    0.45
    POSITIVE LOGITS
     Thumbnail
    0.54
    हमारी
    0.51
    踺
    0.47
    ዐይን
    0.46
     Autobi
    0.45
    ኳ
    0.45
     আমাদের
    0.44
    ፧
    0.43
     Lebensmittel
    0.43
     ialah
    0.42
    Act Density 0.002%

    No Known Activations