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

    Neuronpedia

    INDEX
    Explanations

    asking for a raise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.52
    wert
    0.51
    anilide
    0.50
    ass
    0.49
     areas
    0.48
     ปก
    0.47
    //}
    0.47
    াল
    0.46
    aggregate
    0.46
    াহ
    0.45
    POSITIVE LOGITS
    龴
    0.47
    鸵
    0.45
    මැ
    0.45
    ispens
    0.45
    誅
    0.43
     فیصل
    0.43
     Lune
    0.43
    razione
    0.43
     SLOT
    0.42
     cỏ
    0.41
    Act Density 0.000%

    No Known Activations