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

    Neuronpedia

    INDEX
    Explanations

    and, both, or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cheap
    -0.08
     impro
    -0.08
     வ
    -0.07
     cheaper
    -0.07
     العالية
    -0.07
     impec
    -0.07
    Integr
    -0.07
    封
    -0.07
     gimm
    -0.07
    ilevel
    -0.07
    POSITIVE LOGITS
     רח
    0.10
     Intersection
    0.10
     перечис
    0.08
     dham
    0.08
     Union
    0.08
    _union
    0.08
     Accepted
    0.08
     Mitglieder
    0.08
    Union
    0.08
    Intersection
    0.08
    Act Density 0.028%

    No Known Activations