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

    Neuronpedia

    INDEX
    Explanations

    another

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дает
    -0.06
     hostages
    -0.06
    InnerHTML
    -0.06
    declaring
    -0.06
    	file
    -0.06
     �
    -0.06
     lược
    -0.06
     продовж
    -0.06
    -btn
    -0.06
     liệt
    -0.06
    POSITIVE LOGITS
     Cuban
    0.07
     verilen
    0.07
     Bo
    0.07
    /tests
    0.07
    โรงแรม
    0.07
    ého
    0.07
     Momentum
    0.06
     dusty
    0.06
    ildi
    0.06
    gan
    0.06
    Act Density 0.000%

    No Known Activations