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

    Neuronpedia

    INDEX
    Explanations

    always

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     기록
    -0.07
    oidal
    -0.07
     관심
    -0.07
     düş
    -0.06
     mach
    -0.06
    otic
    -0.06
    EDIATE
    -0.06
     negoci
    -0.06
     getToken
    -0.06
     Пар
    -0.06
    POSITIVE LOGITS
    0.07
    0.06
    
    0.06
    UILT
    0.06
    轉
    0.06
    reesome
    0.06
     gg
    0.06
     cách
    0.06
    getWindow
    0.06
    ainment
    0.06
    Act Density 0.001%

    No Known Activations