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

    Neuronpedia

    INDEX
    Explanations

    mold, latex, Plataformas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alienated
    0.54
    每次
    0.46
     immers
    0.45
     appreciative
    0.44
     oblivious
    0.44
    ing
    0.43
    pathetic
    0.43
    人生
    0.43
    hos
    0.43
     hopeless
    0.43
    POSITIVE LOGITS
     టా
    0.52
    𐰺
    0.52
    қу
    0.50
    ट्
    0.50
     Nahrung
    0.49
     Köln
    0.48
    ᖕ
    0.47
     Detection
    0.47
     Beim
    0.46
     бонус
    0.45
    Act Density 0.000%

    No Known Activations