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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defenders
    -0.08
     환산
    -0.07
     yards
    -0.06
     Install
    -0.06
     contact
    -0.06
    นอ
    -0.06
     vers
    -0.06
    скор
    -0.06
    <this
    -0.06
    .VERTICAL
    -0.06
    POSITIVE LOGITS
    ूरत
    0.07
     MessageLookup
    0.06
    .lines
    0.06
    /debug
    0.06
    _span
    0.06
    營
    0.06
    Elf
    0.06
    Si
    0.06
     MARK
    0.06
    '],
↵
    0.06
    Act Density 0.008%

    No Known Activations