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

    Neuronpedia

    INDEX
    Explanations

    command line outputs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icrobial
    -0.08
    _dtype
    -0.07
     indigenous
    -0.07
     Granted
    -0.07
    =com
    -0.06
     Stre
    -0.06
    ❊
    -0.06
     Give
    -0.06
    Enumeration
    -0.06
    وضح
    -0.06
    POSITIVE LOGITS
    ()}>↵
    0.07
    ButtonModule
    0.07
    BeforeEach
    0.06
    墨西
    0.06
     roleName
    0.06
    比率
    0.06
    ?;↵↵
    0.06
    .Notification
    0.06
    ResponseStatus
    0.06
    iminal
    0.06
    Act Density 0.003%

    No Known Activations