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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _wire
    -0.06
    (VALUE
    -0.06
     witnesses
    -0.06
     Je
    -0.06
    斯
    -0.06
     steak
    -0.06
     wire
    -0.06
    980
    -0.06
     精
    -0.06
    スカ
    -0.06
    POSITIVE LOGITS
    pleted
    0.07
    VM
    0.07
     Hum
    0.07
     famine
    0.06
    超过
    0.06
    cribing
    0.06
    ptime
    0.06
    iven
    0.06
    Reference
    0.06
    vailable
    0.06
    Act Density 0.054%

    No Known Activations