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

    Neuronpedia

    INDEX
    Explanations

    personal information theft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nghĩ
    -0.06
    Dean
    -0.06
    ังกล
    -0.06
     lobbyist
    -0.06
    ambia
    -0.06
     '../../../../
    -0.06
    ethe
    -0.06
    获得
    -0.06
     ста
    -0.06
    “It
    -0.06
    POSITIVE LOGITS
     ナ
    0.07
     SOCK
    0.07
     Tracks
    0.07
     �
    0.07
    史
    0.07
     fh
    0.07
    /init
    0.07
     ins
    0.07
     Succ
    0.07
     Artifact
    0.06
    Act Density 0.016%

    No Known Activations