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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ListOf
    -0.07
    _Post
    -0.06
    _IS
    -0.06
    subj
    -0.06
    _registration
    -0.06
     apopt
    -0.06
     Twist
    -0.06
    termination
    -0.06
    MP
    -0.06
    ektor
    -0.06
    POSITIVE LOGITS
     tedy
    0.06
     mond
    0.06
     hơn
    0.06
     elimin
    0.06
    ávací
    0.06
     ｲ
    0.06
    >
    0.06
     sinc
    0.06
     game
    0.06
     fury
    0.06
    Act Density 0.003%

    No Known Activations