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

    Neuronpedia

    INDEX
    Explanations

    hypothetical statements and possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*
    0.80
    ப்பதை
    0.70
    ="
    0.69
    s
    0.68
     bằng
    0.68
    ח
    0.68
    ))
    0.66
    untary
    0.66
    **)
    0.66
     numquam
    0.66
    POSITIVE LOGITS
    сная
    0.79
    buty
    0.77
    ीडियो
    0.76
    ously
    0.75
    TGFuZ
    0.74
     выс
    0.74
    יות
    0.73
     रिपोर्ट्स
    0.73
     verlei
    0.73
     ആരാധ
    0.71
    Act Density 0.000%

    No Known Activations