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

    Neuronpedia

    INDEX
    Explanations

    calculates difference between numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ايا
    0.54
    }'],
    0.54
    圿
    0.52
    ведена
    0.51
     بیچ
    0.51
     அமைப்பு
    0.50
     arquitectura
    0.50
     Ispol
    0.49
     Jaaye
    0.49
    아야
    0.48
    POSITIVE LOGITS
     grating
    0.52
    -
    0.50
    ids
    0.48
    laub
    0.47
    iet
    0.47
     rating
    0.47
    rating
    0.46
    lgende
    0.46
     cet
    0.46
    ieg
    0.45
    Act Density 0.000%

    No Known Activations