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

    Neuronpedia

    INDEX
    Explanations

    paid, used, read, demanded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻮ
    0.70
    Overview
    0.66
    Listed
    0.62
    Talk
    0.59
    Nom
    0.59
    Education
    0.59
    Over
    0.56
    requ
    0.55
    Requested
    0.55
    (
    0.55
    POSITIVE LOGITS
     ventil
    0.60
    त
    0.59
    п
    0.59
    ด
    0.59
    นั้น
    0.57
     consciously
    0.57
     fend
    0.57
     ecologically
    0.57
     counterv
    0.57
    ,
    0.56
    Act Density 0.078%

    No Known Activations