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

    Neuronpedia

    INDEX
    Explanations

    circles tangent to axes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interfer
    -0.09
    ೇಷ
    -0.09
     Append
    -0.08
    akespe
    -0.08
     выполнять
    -0.08
     מגוון
    -0.08
    acionales
    -0.08
     संविधान
    -0.08
     Presiden
    -0.08
     Umfang
    -0.08
    POSITIVE LOGITS
    靠
    0.09
    inside
    0.09
     insulation
    0.09
    Behind
    0.09
     snug
    0.08
     위치
    0.08
     south
    0.08
     confinement
    0.08
     inward
    0.08
    Radius
    0.08
    Act Density 0.032%

    No Known Activations