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

    Neuronpedia

    INDEX
    Explanations

    making an effort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offend
    -0.07
     Tort
    -0.06
    FFFF
    -0.06
    Bru
    -0.06
     JSGlobal
    -0.06
     دختر
    -0.06
     του
    -0.06
    .Build
    -0.06
    BSD
    -0.06
    orton
    -0.06
    POSITIVE LOGITS
    ımızı
    0.07
     eBooks
    0.07
    (directory
    0.07
    .Rendering
    0.06
    峰
    0.06
     recherche
    0.06
     maint
    0.06
    .fromJson
    0.06
     chances
    0.06
    成本
    0.06
    Act Density 0.028%

    No Known Activations