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

    Neuronpedia

    INDEX
    Explanations

    Text markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    □
    -0.09
     अवस्थ
    -0.09
     dwelling
    -0.08
     Aufent
    -0.08
     meaningless
    -0.08
    қа
    -0.08
     cometido
    -0.08
     hóa
    -0.08
     принять
    -0.08
    'oc
    -0.08
    POSITIVE LOGITS
     USA
    0.11
     bietet
    0.10
     réput
    0.10
    USA
    0.10
     предлагают
    0.10
    Offers
    0.10
     erbjuder
    0.10
     tilbyr
    0.10
     renowned
    0.10
     bieten
    0.09
    Act Density 0.093%

    No Known Activations