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

    Neuronpedia

    INDEX
    Explanations

    rich history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.63
    0.60
    larında
    0.59
    larına
    0.59
    𝘧
    0.58
    larınız
    0.57
     নিজের
    0.57
     אחד
    0.56
    ных
    0.55
    感じる
    0.55
    POSITIVE LOGITS
     History
    0.66
     Rich
    0.63
     rich
    0.61
    k
    0.60
    ha
    0.59
    va
    0.55
    ၊
    0.54
     G
    0.53
     Renderer
    0.53
     Par
    0.53
    Act Density 0.001%

    No Known Activations