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

    Neuronpedia

    INDEX
    Explanations

    code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peg
    -0.07
     '-')
    -0.07
    よね
    -0.07
    _SEL
    -0.06
    EXPECTED
    -0.06
     likeness
    -0.06
     강남
    -0.06
    allenges
    -0.06
    abcdefghijkl
    -0.06
     СП
    -0.06
    POSITIVE LOGITS
    acích
    0.07
    ΙΑΚ
    0.06
     numéro
    0.06
    ениями
    0.06
    entanyl
    0.06
    ÄŸ
    0.06
    ầ
    0.06
    ưu
    0.06
    циях
    0.06
     burgeoning
    0.06
    Act Density 0.000%

    No Known Activations