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

    Neuronpedia

    INDEX
    Explanations

    Other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diary
    -0.06
    -source
    -0.06
     kiểm
    -0.06
     başlat
    -0.06
     Diary
    -0.06
    activation
    -0.06
    ortion
    -0.06
    &uuml
    -0.06
    興
    -0.06
    ję
    -0.06
    POSITIVE LOGITS
     Other
    0.08
    Other
    0.07
    landscape
    0.07
     been
    0.07
    -mf
    0.07
     Premi
    0.06
    ｛
    0.06
     *)((
    0.06
     /[
    0.06
     ')[
    0.06
    Act Density 0.025%

    No Known Activations