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

    Neuronpedia

    INDEX
    Explanations

    Arrays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mitted
    -0.08
     blockers
    -0.08
    _pixels
    -0.07
    .subscribe
    -0.07
     прож
    -0.07
     stores
    -0.07
     несколь
    -0.07
     Appeals
    -0.07
    manifest
    -0.07
     Мин
    -0.07
    POSITIVE LOGITS
    괴
    0.09
    ă
    0.07
    .Dot
    0.07
    gc
    0.07
    スター
    0.07
    ṛ
    0.07
     organization
    0.07
    弃
    0.07
    oyo
    0.07
    ambah
    0.07
    Act Density 0.003%

    No Known Activations