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

    Neuronpedia

    INDEX
    Explanations

    almost certainly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.55
    то
    0.55
    <0x98>
    0.50
    зы
    0.50
     and
    0.50
    م
    0.50
    νο
    0.49
    在
    0.47
    но
    0.47
    त्मक
    0.44
    POSITIVE LOGITS
    źdz
    0.55
     împre
    0.55
     leeftijd
    0.54
     Minggu
    0.53
     ট্র্যাক
    0.52
     informacije
    0.51
    owneri
    0.51
     ziyaret
    0.51
     informace
    0.51
    ernen
    0.50
    Act Density 0.000%

    No Known Activations