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

    Neuronpedia

    INDEX
    Explanations

    academic writing and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卢
    -0.08
    ateful
    -0.08
     COPY
    -0.07
     dø
    -0.07
    Voilà
    -0.07
     divisible
    -0.07
    Totals
    -0.07
     repe
    -0.07
     VISA
    -0.07
     hugely
    -0.07
    POSITIVE LOGITS
     literature
    0.08
     letzten
    0.08
    ^-
    0.07
     Anthrop
    0.07
     This
    0.07
     Fluid
    0.07
    فرنس
    0.07
    _Buffer
    0.07
     ткан
    0.07
     podjet
    0.07
    Act Density 0.026%

    No Known Activations