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

    Neuronpedia

    INDEX
    Explanations

    names or publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Marc
    -0.07
    (stack
    -0.07
    Margin
    -0.06
    [parent
    -0.06
    ine
    -0.06
     brides
    -0.06
     Stephanie
    -0.06
    Mouse
    -0.06
    (rd
    -0.06
    _events
    -0.06
    POSITIVE LOGITS
     invariably
    0.07
     :,
    0.07
     prohibits
    0.06
     arbitration
    0.06
    üş
    0.06
     cứu
    0.06
    ;(
    0.06
    ував
    0.06
     trot
    0.06
     Newsletter
    0.06
    Act Density 0.024%

    No Known Activations