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

    Neuronpedia

    INDEX
    Explanations

    PCR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    חל
    -0.07
     beforehand
    -0.07
    互助
    -0.07
     adoption
    -0.07
     selective
    -0.07
    はじ
    -0.07
    -import
    -0.07
     Hij
    -0.07
    对我
    -0.07
    .length
    -0.07
    POSITIVE LOGITS
     Cologne
    0.08
    财运
    0.07
    ⇛
    0.07
     ou
    0.07
    剕
    0.07
    콱
    0.07
    rms
    0.07
     Ceramic
    0.06
    NonQuery
    0.06
    تويتر
    0.06
    Act Density 0.003%

    No Known Activations