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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Blackhawks
    -0.07
     Arena
    -0.06
     Two
    -0.06
     CJ
    -0.06
    �
    -0.06
    赤
    -0.06
     پاک
    -0.06
     MOR
    -0.06
     FALSE
    -0.06
     Geek
    -0.06
    POSITIVE LOGITS
    Monthly
    0.07
     earners
    0.07
    lahoma
    0.06
    포츠
    0.06
     yüksek
    0.06
     Benjamin
    0.06
    관
    0.06
    stories
    0.06
    (function
    0.06
     Parsing
    0.06
    Act Density 0.012%

    No Known Activations