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

    Neuronpedia

    INDEX
    Explanations

    Spanish how-to phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Konrad
    0.48
     Estud
    0.46
    érique
    0.46
     Sven
    0.46
     Bri
    0.45
    ாரி
    0.44
     qualités
    0.44
     Sen
    0.43
     aston
    0.43
     grows
    0.43
    POSITIVE LOGITS
     插
    0.50
    cutting
    0.50
    ilda
    0.48
    actually
    0.48
    ('
    0.47
    '}
    0.47
    inelli
    0.47
    黔
    0.47
    cut
    0.46
    Increasing
    0.46
    Act Density 0.000%

    No Known Activations