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

    Neuronpedia

    INDEX
    Explanations

    independent phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jika
    0.77
    ες
    0.77
    Arizona
    0.75
    IS
    0.73
    вален
    0.73
    '
    0.72
    εσ
    0.71
    说什么
    0.71
    SA
    0.70
    ESSAGE
    0.69
    POSITIVE LOGITS
     можно
    0.91
     periodontal
    0.87
     🙌
    0.84
     gems
    0.82
     yearn
    0.82
     hardships
    0.81
     несколько
    0.81
     трубы
    0.80
    gems
    0.78
     கட்டுமான
    0.77
    Act Density 0.000%

    No Known Activations