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

    Neuronpedia

    INDEX
    Explanations

    Action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .crm
    -0.07
    ALES
    -0.06
     Hamp
    -0.06
     Sage
    -0.06
     Room
    -0.06
    수
    -0.06
     hòa
    -0.06
    장
    -0.06
     Beetle
    -0.06
    ewidth
    -0.06
    POSITIVE LOGITS
     cual
    0.07
     tho
    0.07
    ovat
    0.07
    عام
    0.07
    Miss
    0.06
     don
    0.06
    ्पत
    0.06
    ạt
    0.06
    gcc
    0.06
    Raster
    0.06
    Act Density 0.003%

    No Known Activations