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

    Neuronpedia

    INDEX
    Explanations

    general writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chores
    -0.07
     représent
    -0.07
    .isDebugEnabled
    -0.07
    Matchers
    -0.06
    たちは
    -0.06
    .inverse
    -0.06
     FLAGS
    -0.06
     نیز
    -0.06
     영어
    -0.06
    .Member
    -0.06
    POSITIVE LOGITS
     conjunction
    0.07
     Tan
    0.07
     pilgrimage
    0.06
    adoop
    0.06
     regenerated
    0.06
    하기
    0.06
     anonym
    0.06
     Petr
    0.06
     fren
    0.06
     xxx
    0.06
    Act Density 0.001%

    No Known Activations