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

    Neuronpedia

    INDEX
    Explanations

    conjunctions, commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     čas
    -0.08
    芝
    -0.07
    -function
    -0.07
    ھ
    -0.07
     availability
    -0.07
    會
    -0.07
    会
    -0.06
     Boundary
    -0.06
    -aligned
    -0.06
    _socket
    -0.06
    POSITIVE LOGITS
     REVIEW
    0.06
     Isle
    0.06
     cận
    0.06
    getSize
    0.06
     ekip
    0.06
     Fold
    0.06
    (pic
    0.06
     bodily
    0.06
     unfairly
    0.06
    Non
    0.06
    Act Density 0.037%

    No Known Activations