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

    Neuronpedia

    INDEX
    Explanations

    verbs ending in -ing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    があれば
    0.51
     Built
    0.45
     Varieties
    0.44
    Built
    0.43
     Various
    0.42
     দখলে
    0.41
    ])/
    0.39
     Calculated
    0.39
     Such
    0.39
    としての
    0.39
    POSITIVE LOGITS
     dealing
    0.99
    dealing
    0.79
     confronted
    0.79
     interacting
    0.77
     greeted
    0.77
     talking
    0.76
     embarking
    0.75
     asked
    0.71
     accessing
    0.70
     surrounded
    0.70
    Act Density 0.253%

    No Known Activations