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
     robber
    -0.07
    echo
    -0.07
     Kostenlose
    -0.06
     Ultimate
    -0.06
     planetary
    -0.06
    яз
    -0.06
     tilt
    -0.06
     CLI
    -0.06
    interp
    -0.06
     Mits
    -0.06
    POSITIVE LOGITS
     sớm
    0.07
     seems
    0.07
    Decoder
    0.06
    셔
    0.06
    ฤษภาคม
    0.06
    .ManyToMany
    0.06
     idiots
    0.06
     seem
    0.06
    PHY
    0.06
    _Camera
    0.06
    Act Density 0.013%

    No Known Activations