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

    Neuronpedia

    INDEX
    Explanations

    Achieving it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atória
    0.49
    валася
    0.48
    पुरम
    0.48
    тила
    0.47
    ർത്ത
    0.47
     искусство
    0.47
     internacionais
    0.45
    𒆳
    0.45
    ofil
    0.44
     jurisdict
    0.43
    POSITIVE LOGITS
     מי
    0.55
     ס
    0.52
     ד
    0.49
     כש
    0.47
     த
    0.47
     ש
    0.47
     Beno
    0.46
     স্ট
    0.45
     یک
    0.45
     mit
    0.45
    Act Density 0.000%

    No Known Activations