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

    Neuronpedia

    INDEX
    Explanations

    challenging problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     %=
    -0.07
     numbered
    -0.07
     pretty
    -0.07
     فران
    -0.06
     sortie
    -0.06
     critique
    -0.06
    ��
    -0.06
    	x
    -0.06
     CLR
    -0.06
    .DELETE
    -0.06
    POSITIVE LOGITS
     Moms
    0.06
    払
    0.06
     QMessageBox
    0.06
     년
    0.06
    esser
    0.06
    년
    0.06
     demanding
    0.06
    uted
    0.06
    수의
    0.06
    El
    0.06
    Act Density 0.071%

    No Known Activations