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

    Neuronpedia

    INDEX
    Explanations

    code/regex/database syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    พ
    -0.08
     defend
    -0.08
    yay
    -0.07
    ивание
    -0.07
    Пер
    -0.07
    .connect
    -0.07
    way
    -0.07
     nation
    -0.07
     dirige
    -0.07
     motherhood
    -0.07
    POSITIVE LOGITS
     resemblance
    0.09
     정보
    0.08
     rigu
    0.07
    ীক্ষ
    0.07
    ────
    0.07
    (kind
    0.07
    mig
    0.07
    āp
    0.07
    ம
    0.07
    360
    0.07
    Act Density 0.005%

    No Known Activations