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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حالت
    -0.08
    mts
    -0.07
     vinden
    -0.07
    ulist
    -0.06
    _find
    -0.06
     протягом
    -0.06
     mentions
    -0.06
    пеки
    -0.06
     budete
    -0.06
     about
    -0.06
    POSITIVE LOGITS
     Thánh
    0.07
    ерим
    0.07
    constraint
    0.07
    .AppendLine
    0.07
    -F
    0.06
     gül
    0.06
    	AL
    0.06
    _GRP
    0.06
     immac
    0.06
    陰
    0.06
    Act Density 0.049%

    No Known Activations