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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     identities
    -0.07
     Following
    -0.06
    ạc
    -0.06
     ولد
    -0.06
     control
    -0.06
     vag
    -0.06
     visitors
    -0.06
    similar
    -0.06
     circum
    -0.06
     difficult
    -0.06
    POSITIVE LOGITS
    [...,
    0.07
     ATTR
    0.07
     RUS
    0.07
    (pi
    0.07
    keywords
    0.07
     комплекс
    0.07
     instal
    0.07
     سان
    0.07
     неск
    0.06
     инт
    0.06
    Act Density 0.008%

    No Known Activations