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

    Neuronpedia

    INDEX
    Explanations

    movie titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     спос
    -0.07
    ixmap
    -0.07
    -service
    -0.07
    щё
    -0.07
    burse
    -0.06
    ak
    -0.06
    AK
    -0.06
     interven
    -0.06
     producer
    -0.06
    calloc
    -0.06
    POSITIVE LOGITS
    anine
    0.06
     základ
    0.06
    خط
    0.06
    śmy
    0.06
     luật
    0.06
     promotional
    0.05
    ับผ
    0.05
     chuẩn
    0.05
    heim
    0.05
    interpret
    0.05
    Act Density 0.013%

    No Known Activations