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

    Neuronpedia

    INDEX
    Explanations

    premier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Therefore
    -0.07
     používá
    -0.06
    $out
    -0.06
    .bid
    -0.06
     cere
    -0.06
    .Compiler
    -0.06
    107
    -0.06
     fully
    -0.06
     discrete
    -0.06
     dõi
    -0.06
    POSITIVE LOGITS
     первого
    0.09
     pierws
    0.08
     první
    0.08
     primo
    0.08
    ADED
    0.07
    ].'
    0.07
    ueva
    0.07
    στηκε
    0.07
     перв
    0.07
     первый
    0.07
    Act Density 0.019%

    No Known Activations