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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'use
    -0.07
    (active
    -0.07
    nerg
    -0.06
    -League
    -0.06
    /spec
    -0.06
    .RunWith
    -0.06
     ecstasy
    -0.06
     Rage
    -0.06
     hookers
    -0.06
     Initially
    -0.06
    POSITIVE LOGITS
     하지
    0.07
     {}\
    0.07
     starred
    0.06
     ماند
    0.06
    CN
    0.06
     полот
    0.06
    \",\
    0.06
     }()↵
    0.06
    _CART
    0.06
     Poster
    0.06
    Act Density 0.012%

    No Known Activations