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

    Neuronpedia

    INDEX
    Explanations

    template variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    łac
    0.65
     financ
    0.64
    ulio
    0.63
    elerini
    0.61
    andosi
    0.60
    lir
    0.58
     lettering
    0.58
     sureties
    0.57
     awhile
    0.57
    osta
    0.57
    POSITIVE LOGITS
    MRI
    0.60
    Municipio
    0.55
    County
    0.54
    номи
    0.52
    бычно
    0.51
    Comfort
    0.50
     still
    0.49
    YYYY
    0.49
    Community
    0.49
    worm
    0.49
    Act Density 0.001%

    No Known Activations