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

    Neuronpedia

    INDEX
    Explanations

    introducing important points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帳に追加
    0.48
     bushings
    0.42
    >)`](
    0.42
    㽚
    0.40
    댓글
    0.40
     стрелец
    0.39
     dunno
    0.39
    珽
    0.39
     rigging
    0.38
    暏
    0.38
    POSITIVE LOGITS
     beho
    0.68
     bears
    0.62
     noteworthy
    0.57
     worth
    0.53
    bears
    0.52
     important
    0.52
     важно
    0.50
     beh
    0.49
    值得
    0.49
    worth
    0.48
    Act Density 0.011%

    No Known Activations