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

    Neuronpedia

    INDEX
    Explanations

    mentions of companies and financial conditions in the context of competition

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

    Followed by capitalized words or sentence starts

    np_acts-logits-general · gemini-2.0-flash

    end of sentence new sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.99
     iſt
    -0.96
     Efq
    -0.95
     ſind
    -0.94
     ſtate
    -0.91
     ſur
    -0.89
     auffi
    -0.89
     raiſ
    -0.88
     houſe
    -0.88
     pleaſure
    -0.87
    POSITIVE LOGITS
     I
    1.09
     IIRC
    0.95
     pretty
    0.94
     maybe
    0.92
     kinda
    0.92
     iirc
    0.88
     Gonna
    0.87
     Maybe
    0.86
     idk
    0.80
    basically
    0.79
    Act Density 0.531%

    No Known Activations