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

    Neuronpedia

    INDEX
    Explanations

    click here to follow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يس
    0.76
    ской
    0.73
     elastomers
    0.72
     budou
    0.70
    ிருக்கும்
    0.68
     umowy
    0.68
     되었
    0.67
     paralyzed
    0.66
     mesmerizing
    0.66
     మరియు
    0.65
    POSITIVE LOGITS
    br
    0.96
    h
    0.93
    n
    0.89
    p
    0.85
    ia
    0.78
    b
    0.76
    i
    0.75
    f
    0.75
    ani
    0.73
    nr
    0.73
    Act Density 0.001%

    No Known Activations