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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     креп
    -0.07
    ｨ
    -0.06
     меропри
    -0.06
    ição
    -0.06
    _bucket
    -0.06
     soutě
    -0.06
    _COOKIE
    -0.06
    ]^
    -0.06
    など
    -0.06
    ＜
    -0.06
    POSITIVE LOGITS
     obsessive
    0.07
     lens
    0.07
    :↵↵
    0.07
     Door
    0.07
    :↵
    0.06
    弥
    0.06
     hosted
    0.06
     Anim
    0.06
    _background
    0.06
     Detective
    0.06
    Act Density 0.004%

    No Known Activations