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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fas
    -0.07
    bullet
    -0.06
     ще
    -0.06
    subset
    -0.06
    Gs
    -0.06
    _Login
    -0.06
    ONA
    -0.06
    /static
    -0.06
    <Test
    -0.06
     Lâm
    -0.05
    POSITIVE LOGITS
     NXT
    0.06
    (gca
    0.06
    .cp
    0.06
     positioning
    0.06
     fools
    0.06
     měli
    0.06
    _variables
    0.06
     perror
    0.06
    (rc
    0.06
     :],
    0.06
    Act Density 0.018%

    No Known Activations