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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .amount
    -0.07
     Knight
    -0.06
     swapping
    -0.06
    "In
    -0.06
    WARD
    -0.06
     amount
    -0.06
    기업
    -0.06
     symmetric
    -0.06
    WS
    -0.06
    jury
    -0.05
    POSITIVE LOGITS
     индивиду
    0.08
     رج
    0.07
     SAY
    0.07
    ]{
    0.07
     glad
    0.07
    ‐‐
    0.07
     }}>
    0.07
     onMouse
    0.06
     awaits
    0.06
     alas
    0.06
    Act Density 0.011%

    No Known Activations