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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DROP
    -0.07
     flowering
    -0.07
     magnets
    -0.07
     unmistak
    -0.07
    藏
    -0.07
    farm
    -0.07
    窑
    -0.07
     bucket
    -0.06
     flags
    -0.06
    ສ
    -0.06
    POSITIVE LOGITS
     verg
    0.07
    衝
    0.07
     unified
    0.06
     Imp
    0.06
     עור
    0.06
    期刊
    0.06
     encodeURIComponent
    0.06
    (\"
    0.06
     wannonce
    0.06
    纂
    0.06
    Act Density 0.099%

    No Known Activations