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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     similarities
    -0.07
    ρία
    -0.07
     Din
    -0.07
     sensit
    -0.06
    oured
    -0.06
    έρα
    -0.06
    	Render
    -0.06
     Ferm
    -0.06
     //////////////////
    -0.06
    resar
    -0.06
    POSITIVE LOGITS
    яз
    0.06
     ['$
    0.06
    ChangeListener
    0.06
     становить
    0.06
    .FormBorderStyle
    0.06
    .long
    0.06
    克
    0.06
     dateFormatter
    0.06
    تب
    0.06
     nbytes
    0.06
    Act Density 0.042%

    No Known Activations