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

    Neuronpedia

    INDEX
    Explanations

    secretly wronged or useless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鲔
    0.53
    髖
    0.49
    鈮
    0.48
    煐
    0.47
     фараз
    0.46
     esimerk
    0.46
     structuring
    0.45
    莴
    0.45
    鳟
    0.45
    矵
    0.44
    POSITIVE LOGITS
     blackmail
    0.49
     secretly
    0.48
    ji
    0.48
     wronged
    0.46
     useless
    0.44
     stupid
    0.44
     hehe
    0.43
    hehe
    0.43
     pretended
    0.43
     traitor
    0.43
    Act Density 0.005%

    No Known Activations