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

    Neuronpedia

    INDEX
    Explanations

    awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fruit
    -0.07
     Support
    -0.07
    旦
    -0.06
    olatile
    -0.06
     вел
    -0.06
    _credentials
    -0.06
     treats
    -0.06
     районе
    -0.06
    _setting
    -0.06
    seed
    -0.06
    POSITIVE LOGITS
     pozem
    0.08
     Body
    0.07
     zjist
    0.07
     hlavy
    0.07
    .skill
    0.07
     $#
    0.07
     해외
    0.06
     Bernstein
    0.06
     sapi
    0.06
    erne
    0.06
    Act Density 0.028%

    No Known Activations