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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fits
    -0.07
     �
    -0.07
    érique
    -0.07
     cancer
    -0.06
     powerful
    -0.06
     Gord
    -0.06
    covered
    -0.06
    hide
    -0.06
    项
    -0.06
    mps
    -0.06
    POSITIVE LOGITS
     beneficiaries
    0.08
    :req
    0.07
    IllegalArgumentException
    0.06
    .getElements
    0.06
    џџџџџџџџџџџџџџџџ
    0.06
    coupon
    0.06
     mó
    0.06
    .readValue
    0.06
     Projects
    0.06
     republik
    0.06
    Act Density 0.056%

    No Known Activations