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

    Neuronpedia

    INDEX
    Explanations

    Huntington

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    徒步
    -0.08
     Iterate
    -0.07
    ผ
    -0.07
    uple
    -0.07
    apper
    -0.07
     happ
    -0.07
    jec
    -0.07
     pos
    -0.07
    西部
    -0.07
    iffer
    -0.07
    POSITIVE LOGITS
    鲖
    0.08
     CONSTRAINT
    0.08
     prominently
    0.07
    꾐
    0.07
     insists
    0.07
    ARG
    0.07
     Reliable
    0.07
     planting
    0.07
     synthesis
    0.07
    -inst
    0.07
    Act Density 0.001%

    No Known Activations