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
    ."""↵
    -0.07
     },↵↵↵
    -0.06
    ách
    -0.06
     элем
    -0.06
     четы
    -0.06
    (O
    -0.06
     kitty
    -0.06
    (z
    -0.06
     boa
    -0.06
     Montgomery
    -0.06
    POSITIVE LOGITS
    挥
    0.07
     refuses
    0.07
    ÔNG
    0.06
     forControlEvents
    0.06
    shore
    0.06
    .Parent
    0.06
    lerinde
    0.06
    YW
    0.06
     surtout
    0.06
    Curve
    0.06
    Act Density 0.013%

    No Known Activations