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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Suz
    -0.07
     crim
    -0.07
    IFIC
    -0.06
    /day
    -0.06
    ;;;;
    -0.06
     των
    -0.06
     Royal
    -0.06
    营业
    -0.06
     звіль
    -0.06
    POSITIVE LOGITS
     Note
    0.11
    Note
    0.10
     footnote
    0.09
    note
    0.09
     lecture
    0.09
     note
    0.08
    NOTE
    0.08
    Answers
    0.08
     notes
    0.08
     نه
    0.07
    Act Density 0.011%

    No Known Activations