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

    Neuronpedia

    INDEX
    Explanations

    Russian word formation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    larghezza
    0.73
    彥
    0.70
    REGIUNE
    0.69
    beatCounter
    0.67
     môžete
    0.65
    titulo
    0.64
    cuando
    0.63
     possibilité
    0.63
     arrondie
    0.63
     imong
    0.62
    POSITIVE LOGITS
     на
    1.04
     в
    1.02
     за
    1.01
     по
    0.97
     с
    0.95
     не
    0.95
     у
    0.93
     а
    0.91
     при
    0.90
     про
    0.90
    Act Density 0.107%

    No Known Activations