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

    Neuronpedia

    INDEX
    Explanations

    other things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ح
    0.96
    没有
    0.96
    er
    0.88
    ने
    0.86
    с
    0.85
    か
    0.84
    ال
    0.84
    ו
    0.83
    נ
    0.83
    다
    0.81
    POSITIVE LOGITS
     sebagainya
    1.13
     whatnot
    1.07
    romeda
    1.05
     andere
    1.02
    ंगाबाद
    1.02
     anderen
    1.00
     سایر
    0.92
    อื่น
    0.87
     secondly
    0.87
     autres
    0.86
    Act Density 27.543%

    No Known Activations