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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vanessa
    -0.08
     Steelers
    -0.08
     group's
    -0.08
    овыми
    -0.08
    овым
    -0.08
     UCS
    -0.07
     ')[
    -0.07
    mlar
    -0.07
     Multip
    -0.07
     '}↵
    -0.07
    POSITIVE LOGITS
     ಹಿನ್ನೆ
    0.08
    田
    0.08
     backgrounds
    0.08
    摩
    0.08
    Mediator
    0.08
     emocion
    0.08
     seaside
    0.07
     দুর্�
    0.07
    Cust
    0.07
     whilst
    0.07
    Act Density 0.003%

    No Known Activations