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

    Neuronpedia

    INDEX
    Explanations

    equals/colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     places
    -0.07
     Willie
    -0.07
     naughty
    -0.07
     Когда
    -0.07
     fields
    -0.06
     WRONG
    -0.06
    凉
    -0.06
     Daily
    -0.06
     Healing
    -0.06
     Heath
    -0.06
    POSITIVE LOGITS
    ply
    0.08
    �
    0.07
    !!}</
    0.07
    ése
    0.06
    ran
    0.06
     Disqus
    0.06
    춘
    0.06
     PLL
    0.06
    uhan
    0.06
    \CMS
    0.06
    Act Density 0.020%

    No Known Activations