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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ------
    -0.07
     slipping
    -0.07
     wonder
    -0.07
    ricks
    -0.07
     lên
    -0.07
    ivial
    -0.07
    erg
    -0.07
     Toggle
    -0.07
    رسی
    -0.06
     --------
    -0.06
    POSITIVE LOGITS
     Authorization
    0.07
     conseguir
    0.06
     dismantle
    0.06
     agreements
    0.06
    leşme
    0.06
     Sara
    0.06
    0.06
     gearing
    0.05
     Semiconductor
    0.05
    women
    0.05
    Act Density 0.005%

    No Known Activations