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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    own
    -0.08
    ldb
    -0.07
     ky
    -0.07
     heav
    -0.06
    loaded
    -0.06
     onion
    -0.06
     espan
    -0.06
     subclass
    -0.06
    acon
    -0.06
     Hutch
    -0.06
    POSITIVE LOGITS
    categories
    0.07
     Emoji
    0.06
     gint
    0.06
     Lob
    0.06
     →
    0.06
    inion
    0.06
     emiss
    0.06
     ※
    0.06
    àng
    0.06
    发布
    0.06
    Act Density 0.038%

    No Known Activations