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

    Neuronpedia

    INDEX
    Explanations

    plex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    สาย
    -0.08
    .Err
    -0.08
    .dirty
    -0.07
    jeta
    -0.07
    世间
    -0.07
     Damian
    -0.07
     prop
    -0.07
     ingin
    -0.07
    奶油
    -0.07
    تجنب
    -0.07
    POSITIVE LOGITS
     "),
    0.07
     explored
    0.07
    ERAL
    0.07
    Completed
    0.07
     Mohammed
    0.07
     ((*
    0.07
     Cole
    0.07
    yclopedia
    0.06
    مال
    0.06
     premises
    0.06
    Act Density 0.000%

    No Known Activations