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

    Neuronpedia

    INDEX
    Explanations

    software errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucing
    -0.07
    sing
    -0.07
     olmayan
    -0.06
     Nil
    -0.06
    Cancel
    -0.06
    nze
    -0.06
     Mens
    -0.06
    explode
    -0.06
     supervise
    -0.06
    ат
    -0.06
    POSITIVE LOGITS
    ESIS
    0.06
     Instruction
    0.06
     обла
    0.06
     attribution
    0.06
     reef
    0.06
    dimension
    0.06
     private
    0.06
    érique
    0.06
     euch
    0.06
    ágina
    0.06
    Act Density 0.034%

    No Known Activations