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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olis
    -0.08
     Institutional
    -0.07
    216
    -0.07
    leneck
    -0.07
    /ar
    -0.06
     enzym
    -0.06
    (rt
    -0.06
    nostic
    -0.06
     immersive
    -0.06
    -as
    -0.06
    POSITIVE LOGITS
     weight
    0.17
     Weight
    0.14
    Weight
    0.10
     WEIGHT
    0.09
    -weight
    0.09
     weights
    0.08
    weight
    0.08
    _weight
    0.07
    Pink
    0.07
    王
    0.06
    Act Density 0.012%

    No Known Activations