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

    Neuronpedia

    INDEX
    Explanations

    Code and informal discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Terrace
    -0.07
     самых
    -0.07
    อเร
    -0.06
    ?>">
↵
    -0.06
    osaurs
    -0.06
     высок
    -0.06
     Вик
    -0.06
     Paging
    -0.06
     рей
    -0.06
     spolup
    -0.06
    POSITIVE LOGITS
    Not
    0.07
    utor
    0.07
    planes
    0.06
    puted
    0.06
     tard
    0.06
     GmbH
    0.06
    Already
    0.06
    Originally
    0.06
    855
    0.06
     subway
    0.06
    Act Density 0.000%

    No Known Activations