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

    Neuronpedia

    INDEX
    Explanations

    Harmful/abusive content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    COLOR
    -0.07
    _wo
    -0.07
    restriction
    -0.06
     Straight
    -0.06
    -bearing
    -0.06
     Kup
    -0.06
     Minimal
    -0.06
    larıyla
    -0.06
     أخرى
    -0.06
     ding
    -0.06
    POSITIVE LOGITS
     @{$
    0.06
     є
    0.06
    .hibernate
    0.06
    rega
    0.06
    ResponseBody
    0.06
     suggestive
    0.06
     цей
    0.06
    ric
    0.06
    meet
    0.06
     tento
    0.06
    Act Density 0.013%

    No Known Activations