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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тра
    -0.07
    かった
    -0.06
     vigilant
    -0.06
    Review
    -0.06
     배
    -0.06
    GIN
    -0.06
                                    
    -0.06
     bgColor
    -0.06
    Will
    -0.06
     rulers
    -0.06
    POSITIVE LOGITS
    ":"","
    0.07
     Engagement
    0.06
    ++){↵
    0.06
    _()↵
    0.06
    stinence
    0.06
    ->__
    0.06
    ;if
    0.06
    _eval
    0.06
    _MUT
    0.06
      ↵↵
    0.06
    Act Density 0.062%

    No Known Activations