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

    Neuronpedia

    INDEX
    Explanations

    patterns and sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	count
    -0.07
    _mix
    -0.06
     combinations
    -0.06
    )+'
    -0.06
     pun
    -0.06
    glyph
    -0.06
     bene
    -0.06
    同じ
    -0.06
     Redistribution
    -0.06
     bu
    -0.06
    POSITIVE LOGITS
     {{↵
    0.07
     UserData
    0.07
    ้องการ
    0.07
    lags
    0.06
    REAT
    0.06
     dokonce
    0.06
    ười
    0.06
     Vernon
    0.06
    529
    0.06
     Anna
    0.06
    Act Density 0.006%

    No Known Activations