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

    Neuronpedia

    INDEX
    Explanations

    requests for sample content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     takich
    0.46
     специальных
    0.45
     Schon
    0.44
     Nous
    0.43
     такі
    0.42
     Allemagne
    0.41
     специальные
    0.41
     abstractions
    0.40
     Mudah
    0.40
     illusions
    0.39
    POSITIVE LOGITS
    Sample
    0.58
     sample
    0.55
     example
    0.51
     सैंपल
    0.51
     template
    0.50
    sample
    0.49
    Template
    0.48
     Sample
    0.47
    template
    0.47
    example
    0.46
    Act Density 0.025%

    No Known Activations