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

    Neuronpedia

    INDEX
    Explanations

    math questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     were
    -0.07
    ус
    -0.06
     �
    -0.06
    .border
    -0.06
     was
    -0.06
    _CAM
    -0.06
     sparse
    -0.06
    ิทยาศาสตร
    -0.06
    —he
    -0.06
    rectangle
    -0.05
    POSITIVE LOGITS
     fibonacci
    0.07
    经营
    0.07
     ├──
    0.06
    eně
    0.06
     llam
    0.06
     aggregator
    0.06
    оград
    0.06
     {});↵↵
    0.06
    ित
    0.06
     rendez
    0.06
    Act Density 0.014%

    No Known Activations