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

    Neuronpedia

    INDEX
    Explanations

    revolution or revolutionary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.97
     а
    0.96
    ве
    0.80
    ماش
    0.76
    ه
    0.75
    ما
    0.74
    ви
    0.73
    با
    0.73
    та
    0.72
     се
    0.72
    POSITIVE LOGITS
     indígen
    1.04
     خمسه
    0.99
     incluido
    0.94
    r
    0.92
    нің
    0.91
    ুয়ারি
    0.88
     cubre
    0.88
    nge
    0.88
     necesariamente
    0.88
    蒨
    0.88
    Act Density 0.000%

    No Known Activations