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

    Neuronpedia

    INDEX
    Explanations

    elephant sanctuaries, shows, or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    з
    1.91
    तम
    1.65
    thed
    1.62
    ções
    1.60
    eer
    1.60
    ս
    1.59
    een
    1.57
    ture
    1.55
    스와
    1.50
    스를
    1.48
    POSITIVE LOGITS
     extremism
    1.81
    Само
    1.79
     predicates
    1.77
     weakens
    1.72
    ﻖ
    1.69
     affidavits
    1.68
     rehearsals
    1.67
     hinders
    1.60
    ﺢ
    1.60
     enthalpies
    1.59
    Act Density 0.001%

    No Known Activations