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

    Neuronpedia

    INDEX
    Explanations

    Object

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ida
    -0.07
     Seamless
    -0.07
     struggle
    -0.07
     чем
    -0.06
     Tinder
    -0.06
    idge
    -0.06
    enda
    -0.06
    ime
    -0.06
     scoff
    -0.06
     pies
    -0.06
    POSITIVE LOGITS
    présent
    0.07
    秫
    0.07
    _OC
    0.07
    明朝
    0.07
    (torch
    0.07
    \Doctrine
    0.07
    깐
    0.06
     verification
    0.06
    سقو
    0.06
    Variables
    0.06
    Act Density 0.001%

    No Known Activations