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

    Neuronpedia

    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Indiana
    -0.07
    石
    -0.07
    Η
    -0.06
    ีฬ
    -0.06
     sean
    -0.06
     humanitarian
    -0.06
    ä
    -0.06
    なた
    -0.06
    jb
    -0.06
     здоров
    -0.06
    POSITIVE LOGITS
    notated
    0.07
     notes
    0.07
    ={<
    0.07
    ?.
    0.07
    _CHECK
    0.06
    .regex
    0.06
    IALOG
    0.06
     imgUrl
    0.06
     knowingly
    0.06
    GO
    0.06
    Act Density 0.040%

    No Known Activations