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

    Neuronpedia

    INDEX
    Explanations

    asking for options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obič
    1.80
     duk
    1.75
     čp
    1.74
     catálogo
    1.71
     množ
    1.68
     pā
    1.66
    涅
    1.66
     −
    1.64
     líqu
    1.63
     calendário
    1.62
    POSITIVE LOGITS
    ous
    2.25
    lly
    2.09
    sthe
    2.08
    rs
    2.03
    lty
    2.01
    ae
    2.00
    c
    1.99
    al
    1.94
    il
    1.93
    ious
    1.93
    Act Density 0.881%

    No Known Activations