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

    Neuronpedia

    INDEX
    Explanations

    challenges acrosshand inDNS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مفید
    0.41
     Oké
    0.40
    GER
    0.38
     GER
    0.38
    parse
    0.38
     util
    0.38
     yun
    0.38
    ｷ
    0.37
    ahid
    0.37
    chas
    0.36
    POSITIVE LOGITS
     blackmail
    0.43
    🗒
    0.41
     प्रतिष्ठ
    0.40
     Protestants
    0.39
     sovereignty
    0.38
     monopolies
    0.38
    )–
    0.37
     খাত
    0.37
    हमने
    0.36
    чках
    0.36
    Act Density 0.001%

    No Known Activations