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

    Neuronpedia

    INDEX
    Explanations

    Measures/metrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plastics
    -0.08
    L
    -0.07
     multiples
    -0.06
    	dist
    -0.06
     ep
    -0.06
     Basel
    -0.06
    ывать
    -0.06
     radiant
    -0.06
     maduras
    -0.06
    _learning
    -0.06
    POSITIVE LOGITS
     *)↵
    0.07
     Automobile
    0.06
    ็กชาย
    0.06
     ",↵
    0.06
     ""},↵
    0.06
    :',↵
    0.06
     isEnabled
    0.06
    shouldBe
    0.06
    _axes
    0.06
    _aligned
    0.06
    Act Density 0.068%

    No Known Activations