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

    Neuronpedia

    INDEX
    Explanations

    url paths with tokens enclosed in curly brackets

    oai_token-act-pair · gemini-2.0-flash

    /{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /$
    -1.54
    /";
    -1.52
    /"+
    -1.49
    /
    -1.48
    /"
    -1.48
    /${
    -1.45
    /'
    -1.41
    /")
    -1.41
    /%
    -1.41
    /");
    -1.41
    POSITIVE LOGITS
    ↵↵
    0.98
     
    0.93
    ↵
    0.92
     "
    0.84
      
    0.80
     The
    0.79
     .
    0.74
     I
    0.68
     a
    0.65
     '
    0.63
    Act Density 0.891%

    No Known Activations