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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uter
    0.53
    ter
    0.46
    igh
    0.46
    utor
    0.46
    ated
    0.45
    ally
    0.44
    tered
    0.43
    tering
    0.43
    of
    0.43
    iters
    0.42
    POSITIVE LOGITS
     industriel
    0.54
     boissons
    0.52
     occhi
    0.52
     negozio
    0.51
     antice
    0.51
     caract
    0.51
     CustB
    0.51
     tanque
    0.50
     tissu
    0.50
    簡単に
    0.50
    Act Density 0.108%

    No Known Activations