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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roy
    -0.07
    Acceleration
    -0.07
    shape
    -0.07
     Do
    -0.07
    side
    -0.07
    .END
    -0.06
     så
    -0.06
     kø
    -0.06
    “So
    -0.06
    Height
    -0.06
    POSITIVE LOGITS
     superb
    0.07
     salopes
    0.07
     ones
    0.07
     one
    0.06
    -def
    0.06
    ेयर
    0.06
     hairst
    0.06
     našich
    0.06
     současné
    0.06
    ん
    0.06
    Act Density 0.014%

    No Known Activations