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

    Neuronpedia

    INDEX
    Explanations

    square brackets, mathematical symbols, and diagram labels

    oai_token-act-pair · gemini-2.0-flash

    \]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ainfi
    -1.24
     myſelf
    -1.17
     enfans
    -1.17
     Monfieur
    -1.17
     himſelf
    -1.16
     étoient
    -1.14
     ſche
    -1.14
     poffible
    -1.12
     feroit
    -1.12
     cauſe
    -1.12
    POSITIVE LOGITS
     pos
    0.67
     '
    0.63
     di
    0.59
     Me
    0.59
     Her
    0.58
     gran
    0.57
     mid
    0.57
     la
    0.55
     el
    0.55
     p
    0.54
    Act Density 0.490%

    No Known Activations