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

    Neuronpedia

    INDEX
    Explanations

    before diving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Because
    0.25
     Owing
    0.22
     BECAUSE
    0.21
     Despite
    0.20
    Because
    0.20
     вследствие
    0.19
     Due
    0.19
     frecuente
    0.19
     According
    0.18
     çünkü
    0.18
    POSITIVE LOGITS
    你会
    0.20
     ecco
    0.19
    ier
    0.19
     there
    0.18
     давайте
    0.17
     we
    0.17
    你會
    0.17
     youll
    0.16
    ल्लाला
    0.16
    an
    0.15
    Act Density 0.111%

    No Known Activations