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

    Neuronpedia

    INDEX
    Explanations

    arise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.65
    Jîn
    -0.59
    PMailer
    -0.58
     ProtoMessage
    -0.58
     CreateTagHelper
    -0.57
     للمعارف
    -0.56
     صوتيه
    -0.56
    Ưu
    -0.56
    dafx
    -0.54
    ➟
    -0.54
    POSITIVE LOGITS
     out
    0.68
    out
    0.59
    enderror
    0.50
     initComponents
    0.48
    DoubleQuotes
    0.47
    FORT
    0.47
    AspNetCore
    0.47
     post
    0.46
     under
    0.45
    getOut
    0.45
    Act Density 0.288%

    No Known Activations