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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    視
    -0.07
    >/
    -0.06
    Vu
    -0.06
    swagger
    -0.06
    🎭
    -0.06
    �
    -0.06
    🚜
    -0.06
    ⚞
    -0.06
    페
    -0.06
    贻
    -0.06
    POSITIVE LOGITS
     pairs
    0.08
    Solid
    0.07
    ’S
    0.07
     Mix
    0.07
    .N
    0.07
    的过程中
    0.07
     Backpack
    0.07
    .attrib
    0.07
     Writes
    0.07
    .K
    0.07
    Act Density 0.184%

    No Known Activations