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

    Neuronpedia

    INDEX
    Explanations

    Code and/or text processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Changing
    -0.07
    Grant
    -0.07
     Grant
    -0.07
    Bin
    -0.07
     joke
    -0.06
     president
    -0.06
    Mad
    -0.06
     �
    -0.06
     few
    -0.06
     Mad
    -0.06
    POSITIVE LOGITS
    (lambda
    0.07
    ФЛ
    0.07
    iii
    0.07
    DOWNLOAD
    0.07
     />';↵
    0.07
    implicit
    0.06
     naï
    0.06
     downs
    0.06
     конструк
    0.06
    .profile
    0.06
    Act Density 0.000%

    No Known Activations