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

    Neuronpedia

    INDEX
    Explanations

    stock market changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бывают
    0.43
    葳
    0.43
    峋
    0.40
    爷爷
    0.39
    ાઇલ
    0.39
     prépuce
    0.39
    GBuf
    0.38
     大家
    0.37
    ではない
    0.37
     заданной
    0.36
    POSITIVE LOGITS
     fell
    0.67
     jumped
    0.59
     went
    0.57
     berada
    0.57
     rose
    0.56
     climbed
    0.54
     ended
    0.54
     plunged
    0.54
    fell
    0.53
     dropped
    0.53
    Act Density 0.006%

    No Known Activations