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

    Neuronpedia

    INDEX
    Explanations

    code structure constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sofern
    0.90
     risulta
    0.84
    ų
    0.81
    ளில்
    0.79
     tabela
    0.79
    cych
    0.77
    增速
    0.76
     atuais
    0.76
    có
    0.73
     kaisi
    0.73
    POSITIVE LOGITS
    DateTimePicker
    0.82
    м
    0.70
                               
    0.70
                                   
    0.70
    END
    0.70
    শালী
    0.68
    FragmentManager
    0.66
    ه
    0.65
     entirely
    0.64
     indispensable
    0.64
    Act Density 0.123%

    No Known Activations