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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pumps
    -0.07
     evaluations
    -0.07
    asso
    -0.06
     automation
    -0.06
    ease
    -0.06
     pokus
    -0.06
    ху
    -0.06
    luet
    -0.06
    yclopedia
    -0.06
    俺は
    -0.06
    POSITIVE LOGITS
     Dez
    0.06
     COMM
    0.06
    reds
    0.06
    DM
    0.06
    KC
    0.06
     مص
    0.06
    collect
    0.06
     مقاله
    0.06
    (sd
    0.06
    ekte
    0.06
    Act Density 0.004%

    No Known Activations