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

    Neuronpedia

    INDEX
    Explanations

    research publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tang
    -0.07
     oui
    -0.07
     glamour
    -0.06
    ani
    -0.06
    िम
    -0.06
    cription
    -0.06
    ivity
    -0.06
    verting
    -0.06
     attracted
    -0.06
    jerne
    -0.06
    POSITIVE LOGITS
    UserCode
    0.07
    多い
    0.07
    oader
    0.06
     midd
    0.06
    nez
    0.06
     Somali
    0.06
    	JOptionPane
    0.06
    Vectors
    0.06
    ErrorException
    0.06
    rules
    0.05
    Act Density 0.027%

    No Known Activations