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

    Neuronpedia

    INDEX
    Explanations

    states or descriptions after 'be' verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Suppression
    0.42
     सिने
    0.41
     untitled
    0.40
     Driven
    0.40
    ሠ
    0.39
     وسی
    0.38
     Privilege
    0.38
     synonyms
    0.38
     jad
    0.38
     вари
    0.37
    POSITIVE LOGITS
     insistent
    0.84
     insisting
    0.73
     adamant
    0.71
     complaining
    0.69
     gracious
    0.66
     insist
    0.65
     abusive
    0.64
     furious
    0.64
     unusually
    0.61
     visibly
    0.60
    Act Density 0.011%

    No Known Activations