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

    Neuronpedia

    INDEX
    Explanations

    Evaluative language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    니
    -0.07
    ivan
    -0.07
     koji
    -0.06
     Bott
    -0.06
     broken
    -0.06
     footprint
    -0.06
     Cant
    -0.06
    811
    -0.06
     bro
    -0.06
     Choices
    -0.06
    POSITIVE LOGITS
     експ
    0.08
    (HttpServletRequest
    0.07
    	get
    0.07
    .USER
    0.06
    RNA
    0.06
    (mask
    0.06
    ับการ
    0.06
     міг
    0.06
    strategy
    0.06
     Workout
    0.06
    Act Density 0.120%

    No Known Activations