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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cela
    -0.07
    	scene
    -0.07
    	ac
    -0.06
    Gem
    -0.06
    _write
    -0.06
     будь
    -0.06
    Anime
    -0.06
     sermon
    -0.06
    band
    -0.06
    аном
    -0.06
    POSITIVE LOGITS
    aju
    0.07
     Steelers
    0.06
     जब
    0.06
    اعت
    0.06
     mistaken
    0.06
    asury
    0.06
     veel
    0.06
    羊
    0.06
     jenis
    0.06
     Encore
    0.06
    Act Density 0.002%

    No Known Activations