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

    Neuronpedia

    INDEX
    Explanations

    quoted speaker or attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서
    1.01
     roupa
    1.00
     canteen
    0.94
     collega
    0.93
    ai
    0.92
     hulp
    0.92
     כן
    0.92
     habl
    0.91
    ’
    0.90
    age
    0.89
    POSITIVE LOGITS
    它
    1.26
    tile
    0.97
    يين
    0.96
    grim
    0.93
     эту
    0.91
    tempat
    0.89
     它
    0.89
    stedet
    0.88
    tid
    0.88
    這一
    0.88
    Act Density 0.000%

    No Known Activations