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

    Neuronpedia

    INDEX
    Explanations

    risk assessment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Residential
    -0.06
     сад
    -0.06
    _publish
    -0.06
     대학
    -0.06
    eným
    -0.06
     Controls
    -0.06
     performans
    -0.06
    iron
    -0.06
     segundos
    -0.06
    عام
    -0.06
    POSITIVE LOGITS
     spd
    0.07
     stip
    0.07
     Chic
    0.06
    πί
    0.06
    upiter
    0.06
     sprintf
    0.06
     supra
    0.06
     ae
    0.06
     [|
    0.06
     Jupiter
    0.06
    Act Density 0.053%

    No Known Activations