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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Creatures
    -0.07
     Assistance
    -0.07
    Entry
    -0.06
    Definitions
    -0.06
     GetById
    -0.06
     McGr
    -0.06
     goods
    -0.06
     Stock
    -0.06
    öy
    -0.06
    ylene
    -0.06
    POSITIVE LOGITS
    مارات
    0.07
    ?)↵↵
    0.06
    311
    0.06
    URA
    0.06
     revisions
    0.06
     converse
    0.06
    のだ
    0.06
     outbound
    0.06
     구
    0.06
    osoph
    0.06
    Act Density 0.018%

    No Known Activations