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

    Neuronpedia

    INDEX
    Explanations

    Prepositions/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SD
    -0.07
     seront
    -0.07
     Briggs
    -0.06
    zel
    -0.06
    iques
    -0.06
    格
    -0.06
    ักงาน
    -0.06
    ÅŸ
    -0.06
    팅
    -0.06
    Need
    -0.05
    POSITIVE LOGITS
    などの
    0.07
     individuals
    0.06
     академ
    0.06
    สาม
    0.06
     estimated
    0.06
     );↵
    0.06
    ?><?
    0.06
    Long
    0.06
    (depth
    0.06
     Three
    0.06
    Act Density 0.001%

    No Known Activations