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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بالا
    0.48
    gest
    0.44
    Gest
    0.44
    ディース
    0.41
    하였
    0.41
    Julie
    0.40
    缦
    0.40
     enduring
    0.40
    imeter
    0.40
    మి
    0.39
    POSITIVE LOGITS
     Bloomington
    0.53
    roskop
    0.49
     oameni
    0.49
     कीमत
    0.46
    ке
    0.46
     bloques
    0.46
     groei
    0.46
     kJ
    0.45
     Aprove
    0.45
     ļ
    0.44
    Act Density 0.001%

    No Known Activations