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

    Neuronpedia

    INDEX
    Explanations

    Cambridge's academic and geographical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ва
    1.05
    1
    0.88
     as
    0.86
     frü
    0.85
    的
    0.84
     soziale
    0.78
    2
    0.77
     ändern
    0.74
     finanz
    0.73
     möglich
    0.71
    POSITIVE LOGITS
    am
    1.27
    न
    1.25
    ர்
    1.18
    ר
    1.17
    em
    1.12
    र
    1.12
    ad
    1.08
    स
    1.04
    ون
    1.00
    ER
    0.98
    Act Density 0.004%

    No Known Activations