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

    Neuronpedia

    INDEX
    Explanations

    reason

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scene
    -0.07
     Fuck
    -0.07
    cname
    -0.07
    ustom
    -0.07
    <Project
    -0.06
     loot
    -0.06
    /boot
    -0.06
    รด
    -0.06
     counterfeit
    -0.06
    proto
    -0.06
    POSITIVE LOGITS
     impairment
    0.07
     경
    0.07
     січня
    0.07
     ER
    0.06
    _services
    0.06
     COL
    0.06
     contrat
    0.06
    ورش
    0.06
    (ii
    0.06
     darn
    0.06
    Act Density 0.038%

    No Known Activations