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

    Neuronpedia

    INDEX
    Explanations

    ose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lev
    -0.07
    Verts
    -0.07
    trys
    -0.06
     pillar
    -0.06
    际
    -0.06
    .rectangle
    -0.06
    .Err
    -0.06
    _QU
    -0.06
    onaut
    -0.06
     Michigan
    -0.06
    POSITIVE LOGITS
    exc
    0.07
    sales
    0.07
    şk
    0.07
    ,t
    0.06
    _gate
    0.06
     agreed
    0.06
    =form
    0.06
    大學
    0.06
    ,index
    0.06
     seeded
    0.06
    Act Density 0.004%

    No Known Activations