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

    Neuronpedia

    INDEX
    Explanations

    feel like, or how things are used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concerted
    0.63
     nascent
    0.61
     myriad
    0.61
     requisite
    0.60
     ostensibly
    0.59
     nefarious
    0.57
     cursory
    0.57
     discernible
    0.55
     exorbitant
    0.55
     suboptimal
    0.55
    POSITIVE LOGITS
     persu
    0.44
     accomplishing
    0.44
     believed
    0.44
     disagree
    0.43
     disobey
    0.42
     succeed
    0.42
     prosper
    0.41
     આપવામાં
    0.41
     overall
    0.41
     grown
    0.41
    Act Density 0.013%

    No Known Activations