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

    Neuronpedia

    INDEX
    Explanations

    Korean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pl
    -0.07
     ■
    -0.07
    avadoc
    -0.06
     Dr
    -0.06
     rejo
    -0.06
     Elk
    -0.06
     kan
    -0.06
    tractive
    -0.06
    уется
    -0.06
     bounds
    -0.06
    POSITIVE LOGITS
    unning
    0.07
     ödem
    0.07
     tert
    0.06
     Lindsay
    0.06
    /core
    0.06
    /community
    0.06
     adec
    0.06
     Tunis
    0.06
     byl
    0.06
     Abort
    0.06
    Act Density 0.002%

    No Known Activations