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

    Neuronpedia

    INDEX
    Explanations

    theme:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tet
    0.64
    town
    0.63
    table
    0.61
    tree
    0.60
    tu
    0.57
    tie
    0.57
    txt
    0.56
    tal
    0.56
    tur
    0.55
    tv
    0.55
    POSITIVE LOGITS
     azione
    0.59
     principali
    0.57
    자
    0.54
    ম
    0.54
     uczni
    0.54
     seves
    0.54
     ০
    0.53
     azienda
    0.53
    im
    0.52
    ção
    0.52
    Act Density 0.038%

    No Known Activations