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

    Neuronpedia

    INDEX
    Explanations

    quality, stability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Tool
    -0.06
     الاتحاد
    -0.06
    変わ
    -0.06
     Tud
    -0.06
    .keras
    -0.06
     ');↵
    -0.06
     reven
    -0.06
    ycz
    -0.06
    enerator
    -0.06
    <Client
    -0.06
    POSITIVE LOGITS
     erh
    0.07
     م
    0.07
    .cl
    0.06
    _adjust
    0.06
     spared
    0.06
     inc
    0.06
    -esteem
    0.06
     receipts
    0.06
    .FILE
    0.06
     titulo
    0.06
    Act Density 0.056%

    No Known Activations