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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iley
    -0.07
     ink
    -0.07
     Scotland
    -0.06
    zk
    -0.06
     Gy
    -0.06
     Haley
    -0.06
     Prayer
    -0.06
     Ireland
    -0.06
    _variation
    -0.06
    ќ
    -0.06
    POSITIVE LOGITS
    _hom
    0.07
     WM
    0.06
    :@"
    0.06
    ACLE
    0.06
     UITableViewDelegate
    0.06
    běhu
    0.06
     primaryStage
    0.06
    de
    0.06
    еты
    0.06
     Whether
    0.06
    Act Density 0.000%

    No Known Activations