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

    Neuronpedia

    INDEX
    Explanations

    transactions related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    0.54
    أ
    0.51
     an
    0.51
     korban
    0.50
    یده
    0.49
    奥
    0.49
    KU
    0.49
     Ferté
    0.49
    ્યાર
    0.47
     Kön
    0.47
    POSITIVE LOGITS
     связанные
    0.63
     basadas
    0.60
     effectuées
    0.59
     amelyek
    0.58
     realizadas
    0.54
    tor
    0.53
     якія
    0.53
     effectués
    0.53
    들이
    0.51
     innych
    0.51
    Act Density 0.112%

    No Known Activations