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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     histories
    -0.07
    aviours
    -0.07
    TestFixture
    -0.06
    otic
    -0.06
     コ
    -0.06
     feature
    -0.06
     form
    -0.06
     picker
    -0.06
    .”↵↵
    -0.06
    ."↵↵
    -0.06
    POSITIVE LOGITS
     seçim
    0.06
     Mehmet
    0.06
    단체
    0.06
    astype
    0.06
     suoi
    0.06
    ερο
    0.06
    Lexer
    0.06
     zx
    0.06
    ashtra
    0.06
    yms
    0.06
    Act Density 0.001%

    No Known Activations