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

    Neuronpedia

    INDEX
    Explanations

    the + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     determinada
    1.04
     milliliters
    0.94
     determinado
    0.88
     seguida
    0.85
    が
    0.83
     determinadas
    0.83
     visitas
    0.82
    Ü
    0.81
    Pakistan
    0.81
    riages
    0.80
    POSITIVE LOGITS
    mselves
    1.28
    ophylline
    1.22
    atrical
    1.01
    oretically
    0.96
    matic
    0.95
    od
    0.88
    odore
    0.84
    orems
    0.80
     brink
    0.80
    atre
    0.80
    Act Density 2.542%

    No Known Activations