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

    Neuronpedia

    INDEX
    Explanations

    academic or school year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    了一个
    0.59
    д
    0.58
     recuerda
    0.57
    մ
    0.57
    ;
    0.56
    ারিত
    0.55
     kuin
    0.55
     verhindern
    0.55
     খেলার
    0.54
     detener
    0.54
    POSITIVE LOGITS
    杪
    0.66
     school
    0.63
     eighties
    0.62
     Endo
    0.59
     assemblies
    0.58
    وال
    0.56
    }(
    0.55
    ونها
    0.55
     Wayne
    0.55
    name
    0.55
    Act Density 0.002%

    No Known Activations