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

    Neuronpedia

    INDEX
    Explanations

    width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ancestral
    -0.08
     증
    -0.07
    (pattern
    -0.06
     Lear
    -0.06
    Gener
    -0.06
     buddies
    -0.06
     interchange
    -0.06
    刷
    -0.06
    Пер
    -0.06
    AUT
    -0.06
    POSITIVE LOGITS
    rootScope
    0.06
    quest
    0.06
    maries
    0.06
     pione
    0.06
     �
    0.06
    benhavn
    0.06
    ój
    0.05
    thora
    0.05
    createFrom
    0.05
    bbbb
    0.05
    Act Density 0.003%

    No Known Activations