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

    Neuronpedia

    INDEX
    Explanations

    the word "indirect"

    oai_token-act-pair · gemini-2.0-flash

    indirect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -1.31
     O
    -1.09
     S
    -1.08
     I
    -1.07
     C
    -1.05
     B
    -1.05
     T
    -1.05
     the
    -1.03
     A
    -1.03
      
    -1.02
    POSITIVE LOGITS
     purpoſe
    2.47
     myſelf
    2.36
     Majefty
    2.28
     itſelf
    2.28
     Monfieur
    2.23
     Efq
    2.22
     houſe
    2.17
     ſtate
    2.17
     Anſ
    2.14
     pleaſure
    2.14
    Act Density 1.850%

    No Known Activations