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

    Neuronpedia

    INDEX
    Explanations

    flavor of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ן
    0.83
    n
    0.82
     are
    0.79
     l
    0.76
     mua
    0.70
    ння
    0.68
    nél
    0.66
     prosed
    0.64
    nr
    0.63
     posible
    0.63
    POSITIVE LOGITS
    ر
    0.82
    ী
    0.78
    '
    0.78
    чним
    0.77
    د
    0.75
    that
    0.74
    flavor
    0.71
    <table>
    0.71
    Flavor
    0.71
    og
    0.70
    Act Density 0.004%

    No Known Activations