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

    Neuronpedia

    INDEX
    Explanations

    defining"}, "explaining", "describing"}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Quadrup
    1.45
     straks
    1.21
     matéria
    1.18
    Ф
    1.16
     аз
    1.14
    ЛА
    1.14
     имеются
    1.13
     Париж
    1.12
     두고
    1.12
    冽
    1.10
    POSITIVE LOGITS
    metik
    1.47
    ো
    1.44
    TION
    1.38
    GEBURTS
    1.36
     impor
    1.36
     البته
    1.35
    ený
    1.32
    estly
    1.32
    ignment
    1.30
    roveň
    1.29
    Act Density 0.000%

    No Known Activations