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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kylie
    -0.08
     Rohingya
    -0.07
     manner
    -0.07
    ایر
    -0.06
     Concepts
    -0.06
     Amerik
    -0.06
     Amen
    -0.06
    /St
    -0.06
     Happy
    -0.06
     NORTH
    -0.06
    POSITIVE LOGITS
    getApplication
    0.07
     signup
    0.07
    	flags
    0.06
    poster
    0.06
    ده
    0.06
    unc
    0.06
    仔
    0.06
     puerto
    0.06
    -pro
    0.06
    uyền
    0.06
    Act Density 0.002%

    No Known Activations