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

    Neuronpedia

    INDEX
    Explanations

    to counter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கட
    0.45
    printk
    0.45
     passagem
    0.43
     typical
    0.41
     antlers
    0.40
     sungai
    0.40
     κύ
    0.40
     companions
    0.39
     actualizado
    0.39
    ವುದ
    0.39
    POSITIVE LOGITS
    Science
    0.43
    If
    0.41
     cient
    0.41
    Assignment
    0.41
    Religion
    0.40
    Allison
    0.40
    Russian
    0.40
    Choosing
    0.40
    When
    0.39
    Hungary
    0.39
    Act Density 0.000%

    No Known Activations