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

    Neuronpedia

    INDEX
    Explanations

    bias and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    飾り
    0.42
    ONOM
    0.42
    naph
    0.41
    creation
    0.39
    0.39
    フォーム
    0.38
    нина
    0.38
    MOUNTAINS
    0.38
    nama
    0.38
    HINSTANCE
    0.38
    POSITIVE LOGITS
     😎
    0.54
     Puerto
    0.46
     descarga
    0.43
     paintball
    0.42
     melee
    0.42
     edgy
    0.42
     💪
    0.41
     تحميل
    0.41
     गंभीर
    0.40
     fuertes
    0.40
    Act Density 0.009%

    No Known Activations