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

    Neuronpedia

    INDEX
    Explanations

    Technical writing/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arDown
    -0.07
     Harlem
    -0.07
    ΕΡ
    -0.07
    .isOpen
    -0.07
    Ш
    -0.06
     Toe
    -0.06
    하기
    -0.06
    مس
    -0.06
    ترك
    -0.06
    حم
    -0.06
    POSITIVE LOGITS
     λο
    0.06
     sic
    0.06
     cardiac
    0.06
    .Base
    0.06
    _USERS
    0.06
     dispersion
    0.06
     Poetry
    0.06
     Slice
    0.06
     judiciary
    0.06
    .Instance
    0.06
    Act Density 0.336%

    No Known Activations