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

    Neuronpedia

    INDEX
    Explanations

    decision

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    重複重複
    -0.07
    Na
    -0.07
    Important
    -0.06
     Dw
    -0.06
     میزان
    -0.06
     голову
    -0.06
    都是
    -0.06
     melan
    -0.06
     Cuando
    -0.06
    道
    -0.06
    POSITIVE LOGITS
    _hero
    0.06
     Bunun
    0.06
    asc
    0.06
    бря
    0.06
    chem
    0.06
    =batch
    0.06
    obook
    0.06
     gelenek
    0.06
    discover
    0.06
     iteration
    0.06
    Act Density 0.052%

    No Known Activations