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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directive
    -0.06
    -med
    -0.06
     Yao
    -0.06
    (messages
    -0.06
    :any
    -0.06
    Aj
    -0.06
    609
    -0.06
    BEST
    -0.06
    CONTROL
    -0.06
    Bur
    -0.06
    POSITIVE LOGITS
    manız
    0.07
    ạnh
    0.07
    years
    0.06
    .Toast
    0.06
     Cannot
    0.06
    /inc
    0.06
    _reads
    0.06
     уг
    0.06
    ",__
    0.06
     tegen
    0.06
    Act Density 0.063%

    No Known Activations