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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aternion
    -0.07
     knees
    -0.06
     hk
    -0.06
    іг
    -0.06
     infinite
    -0.06
     viele
    -0.06
     reading
    -0.06
    distributed
    -0.05
     yapılır
    -0.05
     digital
    -0.05
    POSITIVE LOGITS
    placement
    0.07
    .');
    0.07
    storybook
    0.06
     unins
    0.06
     Sands
    0.06
     Optim
    0.06
    report
    0.06
    ('</
    0.06
     τ
    0.06
     disput
    0.06
    Act Density 0.047%

    No Known Activations