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

    Neuronpedia

    INDEX
    Explanations

    kill, symptoms, shit, drug code words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     event
    0.44
    0.44
     w
    0.43
    в
    0.42
     rejuven
    0.42
     p
    0.41
     c
    0.40
    rb
    0.40
    rs
    0.39
     OEM
    0.39
    POSITIVE LOGITS
    깜
    0.48
    箅
    0.47
    䒠
    0.46
    ሦ
    0.44
     ابتدائي
    0.43
    比赛
    0.43
    雒
    0.43
     වලින්
    0.43
    했고
    0.43
     మూడు
    0.42
    Act Density 0.001%

    No Known Activations