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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    敏
    -0.07
     Airlines
    -0.07
     flew
    -0.07
     fie
    -0.07
    淌
    -0.07
     rhyme
    -0.07
    胎
    -0.07
     exploration
    -0.06
    有网友
    -0.06
     Curriculum
    -0.06
    POSITIVE LOGITS
    规格
    0.08
     deprecated
    0.07
    обыти
    0.07
    copyright
    0.07
    Batch
    0.07
    乙
    0.06
     tabs
    0.06
     pesos
    0.06
    ▬
    0.06
     arrangements
    0.06
    Act Density 0.001%

    No Known Activations