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
     Comparator
    -0.06
    etrofit
    -0.06
    "If
    -0.06
    .Serializer
    -0.06
    “If
    -0.06
    ?>↵
    -0.06
    ellig
    -0.06
    ==============↵
    -0.06
     Giấy
    -0.06
     playful
    -0.06
    POSITIVE LOGITS
     очист
    0.07
    credentials
    0.07
    Quad
    0.07
    Create
    0.07
     Gim
    0.06
    Custom
    0.06
    CNT
    0.06
    istence
    0.06
    �
    0.06
     babes
    0.06
    Act Density 0.013%

    No Known Activations