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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    operands
    -0.07
     respir
    -0.07
    endet
    -0.06
     vigorously
    -0.06
     nue
    -0.06
    Textures
    -0.06
     دری
    -0.06
     oggi
    -0.06
    opies
    -0.06
    ngthen
    -0.05
    POSITIVE LOGITS
    ("(
    0.07
     wanna
    0.07
     mirrored
    0.07
    'b
    0.07
    Advertising
    0.06
     Olympic
    0.06
     RETURNS
    0.06
     stacking
    0.06
    _csv
    0.06
     advertising
    0.06
    Act Density 0.001%

    No Known Activations