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

    Neuronpedia

    INDEX
    Explanations

    code and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wolf
    -0.07
    рест
    -0.07
     Barton
    -0.07
     Berger
    -0.06
     Frankfurt
    -0.06
     Bad
    -0.06
     करत
    -0.06
     ж
    -0.06
    _LOC
    -0.06
    .Direct
    -0.06
    POSITIVE LOGITS
     तम
    0.06
     nga
    0.06
     @{$
    0.06
     advis
    0.06
     beverages
    0.06
     condol
    0.06
     appropriate
    0.06
    IVO
    0.06
     positivity
    0.06
    iya
    0.06
    Act Density 0.024%

    No Known Activations