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

    Neuronpedia

    INDEX
    Explanations

    write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Something
    -0.07
    =""><
    -0.07
    Become
    -0.07
     Releases
    -0.06
    Chocolate
    -0.06
    еред
    -0.06
    ぞ
    -0.06
     Portable
    -0.06
     machines
    -0.06
    .typ
    -0.06
    POSITIVE LOGITS
     humane
    0.07
    InSection
    0.07
     studios
    0.06
     poj
    0.06
    VICES
    0.06
     pant
    0.06
     subtype
    0.06
     aynı
    0.06
     archit
    0.06
    .readdir
    0.06
    Act Density 0.031%

    No Known Activations