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

    Neuronpedia

    INDEX
    Explanations

    solely based on context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    impanan
    0.78
     وإ
    0.78
    ر
    0.77
    とめ
    0.76
     doš
    0.75
     計算
    0.73
    مع
    0.73
    𝙶
    0.72
     aka
    0.70
    মত
    0.70
    POSITIVE LOGITS
    s
    0.88
    ्स
    0.78
     poor
    0.78
    ς
    0.77
     tremendous
    0.76
     ticker
    0.73
     bell
    0.73
     wretched
    0.73
     Prussian
    0.73
     gloom
    0.72
    Act Density 0.000%

    No Known Activations