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

    Neuronpedia

    INDEX
    Explanations

    programming beginner questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     lying
    -0.07
     spep
    -0.07
    ‎
    -0.07
     Dys
    -0.07
     REAL
    -0.07
     ,,
    -0.07
     drama
    -0.06
    ,:),
    -0.06
    Description
    -0.06
    POSITIVE LOGITS
    =========
    0.08
    throat
    0.08
    (thread
    0.08
    ◠
    0.07
     Harden
    0.07
    atore
    0.07
    tures
    0.07
     attribute
    0.07
    rik
    0.07
    etrics
    0.07
    Act Density 0.022%

    No Known Activations