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

    Neuronpedia

    INDEX
    Explanations

    diagram

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iếm
    -0.08
    -kind
    -0.06
     ولك
    -0.06
     onslaught
    -0.06
     セ
    -0.06
    (ans
    -0.06
     сов
    -0.06
    -city
    -0.06
     AppState
    -0.06
    .esp
    -0.06
    POSITIVE LOGITS
     diagram
    0.15
     diagrams
    0.14
     Diagram
    0.11
    Diagram
    0.09
     drawing
    0.09
    uming
    0.09
     chart
    0.08
    FIG
    0.08
     mapa
    0.08
    dig
    0.07
    Act Density 0.004%

    No Known Activations