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

    Neuronpedia

    INDEX
    Explanations

    Verb "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treat
    -0.07
    Pipeline
    -0.06
     Push
    -0.06
    lations
    -0.06
     conversations
    -0.06
    Inf
    -0.06
     Genome
    -0.06
    iatrics
    -0.06
     Random
    -0.06
    .Flat
    -0.06
    POSITIVE LOGITS
    sparse
    0.07
    _Struct
    0.07
    ınızı
    0.07
    (words
    0.07
     Zi
    0.06
     Olson
    0.06
     impaired
    0.06
     PictureBox
    0.06
     loan
    0.06
     airl
    0.06
    Act Density 0.031%

    No Known Activations