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

    Neuronpedia

    INDEX
    Explanations

    Roman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .team
    -0.07
    ehr
    -0.07
     mixes
    -0.07
    ่อย
    -0.06
     řed
    -0.06
     './../
    -0.06
     или
    -0.06
     natuur
    -0.06
     seront
    -0.06
    (intent
    -0.06
    POSITIVE LOGITS
    IRTUAL
    0.07
     очередь
    0.06
     athletic
    0.06
    lick
    0.06
     stalls
    0.06
    Nic
    0.06
     informative
    0.06
    Kate
    0.06
     exactly
    0.06
     UITableView
    0.06
    Act Density 0.021%

    No Known Activations