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

    Neuronpedia

    INDEX
    Explanations

    contracts and agreements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iques
    -0.08
     MUCH
    -0.07
    Spanish
    -0.07
    看待
    -0.07
    铒
    -0.07
     ч
    -0.07
     największy
    -0.06
    -entity
    -0.06
    iframe
    -0.06
     disob
    -0.06
    POSITIVE LOGITS
     Tata
    0.08
    를
    0.08
     fld
    0.08
     negligence
    0.08
     المال
    0.08
     ])
    0.07
     produit
    0.07
    hook
    0.07
    标明
    0.07
    .operations
    0.07
    Act Density 0.023%

    No Known Activations