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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кус
    -0.08
    US
    -0.08
    ATS
    -0.07
    _PUBLIC
    -0.07
    _IList
    -0.07
    _is
    -0.07
    is
    -0.07
    ิส
    -0.07
     antis
    -0.07
    ส
    -0.07
    POSITIVE LOGITS
     do
    0.10
    Do
    0.10
     Do
    0.09
    "Do
    0.09
     don
    0.07
     stubborn
    0.07
    -do
    0.07
    Shop
    0.07
     DO
    0.07
    Opt
    0.07
    Act Density 0.032%

    No Known Activations