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

    Neuronpedia

    INDEX
    Explanations

    statements followed by attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    确定
    0.50
    هر
    0.48
    ১৭
    0.47
    ^{+}\
    0.47
    ότη
    0.47
    arran
    0.46
    ESSIONS
    0.46
    츄
    0.46
    ENT
    0.46
    리에
    0.45
    POSITIVE LOGITS
    at
    0.54
    in
    0.49
     уровня
    0.49
     در
    0.49
    en
    0.48
    y
    0.48
     நேர
    0.44
     stra
    0.43
     کر
    0.43
     ರ
    0.43
    Act Density 0.000%

    No Known Activations