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

    Neuronpedia

    INDEX
    Explanations

    .location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shear
    -0.07
    _minute
    -0.07
    LOOR
    -0.06
    agment
    -0.06
     pornofilm
    -0.06
    _____
    -0.06
     název
    -0.06
     сю
    -0.06
    /Footer
    -0.06
    تل
    -0.06
    POSITIVE LOGITS
    olina
    0.07
    opo
    0.07
     sparing
    0.07
     ط
    0.07
     Bun
    0.06
     attribution
    0.06
     boosts
    0.06
    ्रक
    0.06
    liner
    0.06
                     ↵
    0.06
    Act Density 0.005%

    No Known Activations