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

    Neuronpedia

    INDEX
    Explanations

    items or concepts enclosed in parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    parentheses or brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.57
    !*\
    -0.48
    ))->
    -0.47
     ſtre
    -0.47
    EndInit
    -0.47
    "]))
    -0.46
    ']->
    -0.45
    ']))
    -0.44
    ]^{-
    -0.43
    ]')
    -0.43
    POSITIVE LOGITS
     (
    1.30
    (
    0.96
     ((
    0.96
    （
    0.94
    //(
    0.93
     [(
    0.92
    　(
    0.91
    (\
    0.91
      (
    0.91
    -(
    0.90
    Act Density 0.605%

    No Known Activations