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

    Neuronpedia

    INDEX
    Explanations

    hotels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kud
    -0.08
     snake
    -0.07
     south
    -0.07
     Improve
    -0.07
    .wait
    -0.07
     antibiotics
    -0.07
     career
    -0.07
     organisations
    -0.07
     circles
    -0.07
     bidding
    -0.07
    POSITIVE LOGITS
     playerName
    0.07
    <IM
    0.06
     PTS
    0.06
    acy
    0.06
    .clientY
    0.06
    ∠
    0.06
    +='<
    0.06
     usar
    0.06
     зрозум
    0.06
    اصيل
    0.06
    Act Density 0.017%

    No Known Activations