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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YSIS
    -0.07
    combine
    -0.07
    versible
    -0.06
    LOOR
    -0.06
    -vis
    -0.06
    obili
    -0.06
    ξύ
    -0.06
     Requires
    -0.06
    Optional
    -0.06
     ledger
    -0.06
    POSITIVE LOGITS
    frau
    0.07
     buena
    0.06
    Tele
    0.06
     مقاو
    0.06
     кри
    0.06
    ا�
    0.06
     Москва
    0.06
    ामल
    0.06
    .toolStripMenuItem
    0.05
    ,on
    0.05
    Act Density 0.041%

    No Known Activations