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

    Neuronpedia

    INDEX
    Explanations

    sha256

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    濋
    0.43
    *{-
    0.41
    hygine
    0.40
     وکړئ
    0.38
    PHIA
    0.38
    👟
    0.38
     chromosomal
    0.38
     النق
    0.38
    🗣
    0.38
    跄
    0.38
    POSITIVE LOGITS
    un
    0.52
     sha
    0.49
     SHA
    0.48
     ша
    0.48
    Sha
    0.46
    sha
    0.45
    shaft
    0.43
    シャ
    0.42
     שא
    0.42
     don
    0.41
    Act Density 0.006%

    No Known Activations