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

    Neuronpedia

    INDEX
    Explanations

    code and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fra
    -0.06
    _emit
    -0.06
     diver
    -0.06
    .Ed
    -0.06
     factories
    -0.06
    ran
    -0.06
    谈
    -0.06
     accommod
    -0.06
     shocks
    -0.06
    _HEAD
    -0.06
    POSITIVE LOGITS
    Digite
    0.07
    �
    0.07
     TOK
    0.06
    注册
    0.06
     总
    0.06
    hattan
    0.06
     assembler
    0.06
    AndUpdate
    0.06
     использовать
    0.06
    จ
    0.06
    Act Density 0.000%

    No Known Activations