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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mahmoud
    -0.08
    decode
    -0.07
     upheld
    -0.07
     pedigree
    -0.07
     Newsp
    -0.06
     avalanche
    -0.06
    antry
    -0.06
    house
    -0.06
    葱
    -0.06
     mmap
    -0.06
    POSITIVE LOGITS
    angers
    0.07
    這個
    0.07
    brities
    0.06
    .Claims
    0.06
     blir
    0.06
     iOS
    0.06
    𝓁
    0.06
    ♍
    0.06
     פר
    0.06
    iała
    0.06
    Act Density 0.001%

    No Known Activations