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

    Neuronpedia

    INDEX
    Explanations

    the word "type" in code

    oai_token-act-pair · gemini-2.0-flash

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.48
     Efq
    -1.48
     pleaſure
    -1.47
     Jefus
    -1.47
     itſelf
    -1.44
     Majefty
    -1.41
     photolibrary
    -1.39
     Monfieur
    -1.34
     purpoſe
    -1.34
     Anſ
    -1.33
    POSITIVE LOGITS
    ↵
    0.69
     base
    0.67
     
    0.66
     (
    0.64
     this
    0.63
     [
    0.63
     Da
    0.61
     =
    0.61
     Ter
    0.60
     lo
    0.59
    Act Density 0.711%

    No Known Activations