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

    Neuronpedia

    INDEX
    Explanations

    configuration code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     демо
    -0.07
    oked
    -0.07
    팁
    -0.07
    👣
    -0.07
     estratég
    -0.07
    (argc
    -0.07
    objc
    -0.06
    ناقش
    -0.06
     Energ
    -0.06
    迫使
    -0.06
    POSITIVE LOGITS
     Mutation
    0.07
    IVERS
    0.07
    ))^
    0.07
    ndon
    0.06
    찟
    0.06
     Hannah
    0.06
     additive
    0.06
    _DM
    0.06
    ]),↵
    0.06
     Adapter
    0.06
    Act Density 0.026%

    No Known Activations