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

    Neuronpedia

    INDEX
    Explanations

    to confirm removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    阪
    0.77
    en
    0.71
    ႈ
    0.68
    litt
    0.66
    ден
    0.64
    י
    0.62
    ان
    0.62
    oods
    0.61
    italization
    0.61
    oral
    0.60
    POSITIVE LOGITS
     posteriormente
    0.93
     quilted
    0.88
     laminated
    0.87
     oferece
    0.84
     grained
    0.84
     Norbert
    0.82
     modernas
    0.82
     cabelos
    0.82
     pecans
    0.80
     equipamento
    0.80
    Act Density 0.001%

    No Known Activations