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

    Neuronpedia

    INDEX
    Explanations

    opensource

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plit
    -0.07
    puts
    -0.07
    _notes
    -0.07
    ections
    -0.07
     transient
    -0.06
     tattoo
    -0.06
    visitor
    -0.06
    grey
    -0.06
    ήν
    -0.06
    än
    -0.06
    POSITIVE LOGITS
    opensource
    0.12
     Billing
    0.07
    .opensource
    0.07
    赢
    0.06
    .btnCancel
    0.06
    اس
    0.06
    larınız
    0.06
     OSS
    0.06
    ूब
    0.06
    211
    0.06
    Act Density 0.000%

    No Known Activations