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

    Neuronpedia

    INDEX
    Explanations

    React from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стями
    0.43
     pertanto
    0.43
     określ
    0.42
     estremamente
    0.41
     ত্বক
    0.41
    NaHCO
    0.39
     ಬಹಳ
    0.38
    ໃຊ
    0.38
     undertaken
    0.38
     importation
    0.38
    POSITIVE LOGITS
     from
    0.73
     från
    0.65
    from
    0.61
     dari
    0.56
     desde
    0.49
     {
    0.48
    ,
    0.48
    }
    0.47
     من
    0.45
    고
    0.44
    Act Density 0.001%

    No Known Activations