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

    Neuronpedia

    INDEX
    Explanations

    First-person perspective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    озвращает
    -0.06
    .getPath
    -0.06
     mannen
    -0.06
     Mercer
    -0.06
    UCKET
    -0.06
     WITH
    -0.06
     всі
    -0.06
    .IsMatch
    -0.06
    Greek
    -0.06
    MOVED
    -0.06
    POSITIVE LOGITS
     Proceedings
    0.07
    겠습니다
    0.07
    ยง
    0.06
     необ
    0.06
    iceps
    0.06
    :checked
    0.06
     né
    0.06
     contrace
    0.06
    Fully
    0.06
    kop
    0.06
    Act Density 0.031%

    No Known Activations