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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Element
    -0.07
    Jump
    -0.07
     BufferedImage
    -0.07
     jun
    -0.06
     Initialize
    -0.06
     painful
    -0.06
    .readValue
    -0.06
    ยอม
    -0.06
    扫
    -0.06
    .Manager
    -0.06
    POSITIVE LOGITS
    irling
    0.07
     streamline
    0.07
    _flux
    0.07
     hazırl
    0.07
    下周
    0.07
     recycled
    0.07
    情人
    0.07
    ADC
    0.07
     Marketing
    0.07
    UART
    0.06
    Act Density 0.003%

    No Known Activations