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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -no
    -0.07
    ,q
    -0.07
     slows
    -0.06
    ën
    -0.06
    850
    -0.06
    795
    -0.06
    _CAPACITY
    -0.06
    Mod
    -0.06
    _super
    -0.06
     Boone
    -0.06
    POSITIVE LOGITS
     Horror
    0.07
     Druh
    0.06
    ressing
    0.06
    (Request
    0.06
    [f
    0.06
     \<^
    0.06
    .Where
    0.06
     Search
    0.06
     Dup
    0.06
     Classroom
    0.06
    Act Density 0.096%

    No Known Activations