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

    Neuronpedia

    INDEX
    Explanations

    Mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SPA
    -0.07
    架
    -0.07
    chemistry
    -0.06
    燈
    -0.06
    .embed
    -0.06
     из
    -0.06
     Ye
    -0.06
     cushion
    -0.06
     ,"
    -0.06
    告
    -0.06
    POSITIVE LOGITS
     heartfelt
    0.08
    ritable
    0.07
    入园
    0.07
    .true
    0.07
    浲
    0.07
    浓浓的
    0.07
    rnd
    0.07
    Paren
    0.07
     sortOrder
    0.07
     funky
    0.07
    Act Density 0.021%

    No Known Activations