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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    codile
    -0.07
     торгів
    -0.07
     smoothing
    -0.06
    enské
    -0.06
    eder
    -0.06
    명의
    -0.06
     nä
    -0.06
    _Login
    -0.06
     Вони
    -0.06
    .any
    -0.06
    POSITIVE LOGITS
     peaceful
    0.07
     constexpr
    0.07
    .SelectedValue
    0.06
     nécess
    0.06
    Best
    0.06
    (sequence
    0.06
    _beam
    0.06
     客
    0.06
     aussi
    0.06
    	rows
    0.06
    Act Density 0.024%

    No Known Activations