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

    Neuronpedia

    INDEX
    Explanations

    layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lix
    -0.08
     fö
    -0.06
    Jack
    -0.06
     Nose
    -0.06
    '*
    -0.06
    Envelope
    -0.06
     Tod
    -0.06
     successors
    -0.06
    орм
    -0.06
    -sum
    -0.06
    POSITIVE LOGITS
    _ai
    0.07
    副
    0.06
     versus
    0.06
     AUT
    0.06
     reinst
    0.06
    getY
    0.06
    ilers
    0.06
    мі
    0.06
    asley
    0.06
     udělat
    0.06
    Act Density 0.016%

    No Known Activations