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

    Neuronpedia

    INDEX
    Explanations

    inciting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condominium
    -0.07
    Pass
    -0.07
     steward
    -0.07
     وضع
    -0.06
     mandates
    -0.06
    _GPU
    -0.06
    centroid
    -0.06
    Trying
    -0.06
    Comment
    -0.06
    ))↵↵↵
    -0.06
    POSITIVE LOGITS
    017
    0.07
    ächst
    0.06
    oq
    0.06
     гот
    0.06
    !!,
    0.06
     李
    0.06
    ky
    0.06
     headers
    0.06
    UNET
    0.06
    _DEFINE
    0.06
    Act Density 0.010%

    No Known Activations