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

    Neuronpedia

    INDEX
    Explanations

    positive reviews and family references

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.07
     reaſon
    -1.04
     EconPapers
    -1.01
     purpoſe
    -1.01
     poffible
    -1.00
     Anſ
    -0.99
     auffi
    -0.98
     pleaſure
    -0.93
     ſeveral
    -0.91
     themſelves
    -0.91
    POSITIVE LOGITS
     
    0.54
     sou
    0.51
     i
    0.49
     only
    0.49
     bo
    0.49
     “
    0.48
     ‘
    0.47
     far
    0.47
    typeparam
    0.47
     k
    0.46
    Act Density 0.544%

    No Known Activations