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

    Neuronpedia

    INDEX
    Explanations

    programming questions and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nouns
    -0.07
     trait
    -0.07
    .seed
    -0.07
    رف
    -0.06
     primes
    -0.06
     gam
    -0.06
    _learn
    -0.06
    collector
    -0.06
    ें↵↵
    -0.06
    shape
    -0.06
    POSITIVE LOGITS
    ewolf
    0.06
     tranquil
    0.06
     happiest
    0.06
    کری
    0.06
     Shuttle
    0.06
     HIM
    0.06
    swap
    0.06
    ents
    0.06
    جاج
    0.06
    opsis
    0.06
    Act Density 0.028%

    No Known Activations