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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    宏
    -0.07
    aksi
    -0.07
    <Vec
    -0.06
    康
    -0.06
    EndTime
    -0.06
     Sci
    -0.06
    人が
    -0.06
     Vec
    -0.06
    巴
    -0.06
     DeV
    -0.06
    POSITIVE LOGITS
    /setup
    0.07
     schem
    0.07
    صح
    0.07
    seealso
    0.07
    ulers
    0.07
     athe
    0.07
    ystatechange
    0.07
    (policy
    0.06
     Sunny
    0.06
     peaked
    0.06
    Act Density 0.000%

    No Known Activations