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

    Neuronpedia

    INDEX
    Explanations

    the word "thereof" within technical writing

    oai_token-act-pair · gemini-2.0-flash

    thereof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -1.46
    s
    -1.18
     (
    -1.17
      
    -1.13
    ↵↵
    -1.09
    1
    -1.06
    ,
    -1.02
    ↵
    -1.02
    .
    -1.00
    2
    -0.95
    POSITIVE LOGITS
     myſelf
    2.11
     Monfieur
    2.05
     Jefus
    2.02
     Efq
    2.00
     itſelf
    1.96
     Majefty
    1.94
     Houſe
    1.87
     iſt
    1.84
     raiſ
    1.83
     pleaſure
    1.81
    Act Density 0.507%

    No Known Activations