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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đo
    -0.07
    "/>.↵
    -0.07
     motorists
    -0.06
    :{
↵
    -0.06
     discrepan
    -0.06
    óng
    -0.06
    (ExpectedConditions
    -0.06
    -0.06
     tud
    -0.06
    _WARN
    -0.06
    POSITIVE LOGITS
     europe
    0.07
    _pred
    0.06
    gate
    0.06
    -notch
    0.06
    ocha
    0.06
    rika
    0.06
     brilliantly
    0.06
     elev
    0.06
    rais
    0.06
    ocrine
    0.06
    Act Density 0.005%

    No Known Activations