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

    Neuronpedia

    INDEX
    Explanations

    Movement and location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Schedulers
    -0.07
     medical
    -0.07
    Ｒ
    -0.06
     bees
    -0.06
     Tutorial
    -0.06
    .L
    -0.06
    members
    -0.06
     taxable
    -0.06
    Scheduler
    -0.06
    group
    -0.06
    POSITIVE LOGITS
     ".
    0.07
     cara
    0.06
    alıdır
    0.06
     genus
    0.06
    pha
    0.06
     좋
    0.06
    ussia
    0.06
     цін
    0.06
    MH
    0.06
    mh
    0.06
    Act Density 0.059%

    No Known Activations