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

    Neuronpedia

    INDEX
    Explanations

    Conditional context/safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offsetX
    -0.07
    іл
    -0.07
    .animation
    -0.07
    RU
    -0.06
     aluminium
    -0.06
     inve
    -0.06
     hone
    -0.06
     chores
    -0.06
    Qui
    -0.06
    (';
    -0.06
    POSITIVE LOGITS
    στο
    0.07
     unrecognized
    0.07
    整个
    0.06
    /B
    0.06
    -Benz
    0.06
    циональ
    0.06
    imately
    0.06
     transportation
    0.06
    _FM
    0.06
    -components
    0.06
    Act Density 0.000%

    No Known Activations