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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isodes
    -0.07
    کیل
    -0.06
    -On
    -0.06
    况
    -0.06
    瓜
    -0.06
    orrar
    -0.06
     lun
    -0.06
    imi
    -0.06
    کور
    -0.06
     مور
    -0.06
    POSITIVE LOGITS
    allax
    0.07
     Mam
    0.06
     erhalten
    0.06
    vecs
    0.06
     GLint
    0.06
    (encoding
    0.06
    :selected
    0.06
     diluted
    0.06
     celib
    0.06
    Vectors
    0.06
    Act Density 0.004%

    No Known Activations