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

    Neuronpedia

    INDEX
    Explanations

    dump, _r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $($
    -0.07
    $count
    -0.07
    ารย
    -0.07
     Lone
    -0.07
     مر
    -0.07
    抗
    -0.07
     개
    -0.07
     مرتب
    -0.07
    quot
    -0.07
    hift
    -0.07
    POSITIVE LOGITS
     agony
    0.06
     swift
    0.06
    htags
    0.06
    _when
    0.06
    cookies
    0.06
    anner
    0.06
    forcer
    0.06
    @"↵
    0.06
    _TAG
    0.06
    CollectionView
    0.06
    Act Density 0.003%

    No Known Activations