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

    Neuronpedia

    INDEX
    Explanations

    representative example list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (path
    -0.06
    -*-
    -0.06
    itto
    -0.06
    ')
↵
↵
    -0.06
    isos
    -0.06
     Bayer
    -0.06
    軍
    -0.06
    ,p
    -0.06
    Tri
    -0.06
     potions
    -0.06
    POSITIVE LOGITS
    .buf
    0.07
    hr
    0.06
     hourly
    0.06
    	es
    0.06
     BPM
    0.06
    CFG
    0.06
     Samurai
    0.06
     فعالیت
    0.06
    Thousands
    0.06
    |unique
    0.06
    Act Density 0.072%

    No Known Activations