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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yarı
    -0.07
    &uuml
    -0.06
     Kylie
    -0.06
     Link
    -0.06
    _stride
    -0.06
     +#+#+#+#+#+
    -0.06
     obsah
    -0.06
     которое
    -0.06
     شكل
    -0.06
    ']?>"
    -0.06
    POSITIVE LOGITS
    の方
    0.07
     poker
    0.07
    Observable
    0.07
     threw
    0.07
     clin
    0.07
    abee
    0.07
     
    0.07
    PARAM
    0.06
     =====
    0.06
     Linux
    0.06
    Act Density 0.004%

    No Known Activations