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

    Neuronpedia

    INDEX
    Explanations

    [REDACTED]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***
    0.60
     ****
    0.52
     **
    0.52
     undisclosed
    0.48
     [*
    0.46
     [
    0.45
     unseen
    0.44
     quietly
    0.44
     covert
    0.44
     '**
    0.42
    POSITIVE LOGITS
     conséquences
    0.41
     inför
    0.41
    荒
    0.40
    楽し
    0.40
     イラスト
    0.39
    谊
    0.39
    ísima
    0.39
    óság
    0.38
    誼
    0.38
    żd
    0.38
    Act Density 0.002%

    No Known Activations