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

    Neuronpedia

    INDEX
    Explanations

    off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hari
    0.42
    Oste
    0.42
     sobą
    0.41
    क्
    0.40
    கோவை
    0.40
    Infos
    0.39
    Grazie
    0.39
    लखनऊ
    0.38
    フォルダ
    0.38
    ＄
    0.38
    POSITIVE LOGITS
    ensive
    0.82
    izielle
    0.80
     kil
    0.71
    ensively
    0.69
    handedly
    0.65
     Off
    0.61
     beaten
    0.61
    icial
    0.61
    ici
    0.59
     course
    0.59
    Act Density 0.017%

    No Known Activations