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

    Neuronpedia

    INDEX
    Explanations

    describing complexity or behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thunder
    0.55
    iv
    0.50
     bhavanti
    0.50
     helmet
    0.49
     قناه
    0.48
     abstraction
    0.48
     thunderstorms
    0.47
     about
    0.47
     channels
    0.47
    ファイル
    0.47
    POSITIVE LOGITS
    紧急
    0.43
     Anywhere
    0.42
    Julia
    0.41
    并发
    0.41
    ‑
    0.41
     Lep
    0.40
    inge
    0.40
     paylaş
    0.40
     ওভার
    0.39
    nější
    0.39
    Act Density 0.000%

    No Known Activations