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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    として
    -0.07
    までの
    -0.07
    ﲡ
    -0.07
    最初的
    -0.06
     prosecutor
    -0.06
    꺼
    -0.06
    יצה
    -0.06
    Ề
    -0.06
    فاعل
    -0.06
     thúc
    -0.06
    POSITIVE LOGITS
    OU
    0.07
    ў
    0.07
     LV
    0.07
     Shorts
    0.07
     crumbs
    0.07
    .emit
    0.07
    侴
    0.07
     chrom
    0.07
     surrogate
    0.07
     slaves
    0.07
    Act Density 0.005%

    No Known Activations