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

    Neuronpedia

    INDEX
    Explanations

    discussions involving race relations and political commentary

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

    preceding verbs or auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    pronoun/noun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilise
    -0.83
     poichè
    -0.82
     utilising
    -0.81
     endast
    -0.80
     içerisinde
    -0.78
     ifrån
    -0.77
     utilize
    -0.76
     souhaitent
    -0.76
    快速的
    -0.73
     utilised
    -0.73
    POSITIVE LOGITS
     doubtless
    0.68
     exult
    0.67
     cheerfully
    0.65
     coö
    0.65
     impert
    0.65
     sundry
    0.62
     thereupon
    0.62
     cav
    0.62
     drago
    0.62
    بدو
    0.61
    Act Density 0.811%

    No Known Activations