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

    Neuronpedia

    INDEX
    Explanations

    building on itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হোয়াটসঅ্যাপ
    0.52
     ordenador
    0.50
     instante
    0.49
     свой
    0.47
     angular
    0.47
     milliseconds
    0.47
     усилия
    0.47
     तुमचा
    0.46
     át
    0.45
     aplicativo
    0.45
    POSITIVE LOGITS
    شور
    0.54
    Street
    0.49
     ১৯
    0.48
    ice
    0.47
    o
    0.46
    u
    0.45
    *}
    0.44
    Silver
    0.44
    III
    0.44
    ash
    0.43
    Act Density 0.002%

    No Known Activations