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

    Neuronpedia

    INDEX
    Explanations

    past-tense or past-participle verbs

    oai_token-act-pair · gemini-2.0-flash

    Actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slaughtered
    -1.38
     emptied
    -1.37
     popped
    -1.36
     swapped
    -1.36
     demolished
    -1.34
     hanged
    -1.31
     sacrificed
    -1.29
     uninstalled
    -1.28
     deported
    -1.28
     fainted
    -1.27
    POSITIVE LOGITS
     break
    0.73
     drop
    0.71
     take
    0.69
     move
    0.67
     up
    0.61
     turn
    0.61
     start
    0.60
     out
    0.59
     run
    0.58
                                   
    0.58
    Act Density 2.561%

    No Known Activations