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

    Neuronpedia

    INDEX
    Explanations

    fill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Know
    -0.07
     підприємств
    -0.06
    imers
    -0.06
     Sanayi
    -0.06
    phis
    -0.06
     ForeignKey
    -0.06
     Tall
    -0.06
     полит
    -0.06
     کیفیت
    -0.06
     Winner
    -0.06
    POSITIVE LOGITS
     Complete
    0.07
     haunted
    0.06
     handle
    0.06
     COMPLETE
    0.06
    .FixedSingle
    0.06
    Rachel
    0.06
    _mi
    0.06
    /use
    0.06
     Little
    0.06
    Complete
    0.06
    Act Density 0.018%

    No Known Activations