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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deity
    -0.07
     independents
    -0.07
    urgeon
    -0.07
     guesses
    -0.07
     Alf
    -0.07
    <Character
    -0.06
     Yong
    -0.06
     esl
    -0.06
     Garr
    -0.06
    똑
    -0.06
    POSITIVE LOGITS
     álbum
    0.07
    人际
    0.07
    Footer
    0.07
    صعب
    0.07
    igung
    0.06
    쿱
    0.06
     secure
    0.06
    xFA
    0.06
     beautiful
    0.06
    岽
    0.06
    Act Density 0.020%

    No Known Activations