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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (icon
    -0.07
    _above
    -0.07
     beginning
    -0.07
    After
    -0.06
    ег
    -0.06
     ici
    -0.06
    .MenuItem
    -0.06
    _checksum
    -0.06
    .bridge
    -0.06
     lại
    -0.06
    POSITIVE LOGITS
     panda
    0.08
    IAM
    0.07
     �
    0.06
     GFX
    0.06
     jede
    0.06
     (!!
    0.06
     obl
    0.06
     ट
    0.06
     commod
    0.06
     Ptr
    0.06
    Act Density 0.049%

    No Known Activations