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

    Neuronpedia

    INDEX
    Explanations

    os

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stories
    -0.07
    Print
    -0.06
     ～
    -0.06
    時代
    -0.06
     erotic
    -0.06
    iid
    -0.06
     parallel
    -0.06
     世界
    -0.06
     EW
    -0.06
    Daily
    -0.06
    POSITIVE LOGITS
    removeAttr
    0.07
    adds
    0.07
    äsent
    0.06
    ;if
    0.06
    asjon
    0.06
    ogens
    0.06
     infl
    0.06
    rnek
    0.06
     กระ
    0.06
    (Uri
    0.06
    Act Density 0.017%

    No Known Activations