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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ")
    -0.07
     mig
    -0.07
    }"
    -0.07
    З
    -0.07
     Evelyn
    -0.07
     Your
    -0.06
    utes
    -0.06
    _trans
    -0.06
    )"
    -0.06
     sustained
    -0.06
    POSITIVE LOGITS
     국제
    0.08
     двиг
    0.07
    CGFloat
    0.06
    >'+↵
    0.06
     chac
    0.06
    錯
    0.06
     nbr
    0.06
    -describedby
    0.06
    ToolStripMenuItem
    0.06
    .GetEnumerator
    0.06
    Act Density 0.017%

    No Known Activations