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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ([
    -0.07
     surgeons
    -0.07
     IRA
    -0.07
     кора
    -0.07
     комнат
    -0.07
     робити
    -0.07
     три
    -0.06
     shimmer
    -0.06
    alink
    -0.06
    ucher
    -0.06
    POSITIVE LOGITS
    -в
    0.06
    321
    0.06
    JO
    0.06
     wavelengths
    0.06
    tes
    0.06
    oples
    0.06
     Transformation
    0.06
     participated
    0.06
     gathering
    0.06
     vriend
    0.05
    Act Density 0.101%

    No Known Activations