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

    Neuronpedia

    INDEX
    Explanations

    circumvention of rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HS
    -0.06
    .Serve
    -0.06
    ्वत
    -0.06
    blob
    -0.06
     contagious
    -0.06
     наблю
    -0.06
     noticeable
    -0.06
    _me
    -0.06
     Roh
    -0.06
    ฤศจ
    -0.05
    POSITIVE LOGITS
     evade
    0.08
    Af
    0.06
    lendirme
    0.06
    Beat
    0.06
    (nr
    0.06
    ipers
    0.06
     emerg
    0.06
    的情
    0.06
    DUCT
    0.06
     circ
    0.06
    Act Density 0.008%

    No Known Activations