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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    nande
    -0.08
    earning
    -0.08
     Már
    -0.08
     приход
    -0.08
    nasium
    -0.08
     уход
    -0.07
     BAS
    -0.07
    boost
    -0.07
    nesium
    -0.07
    POSITIVE LOGITS
    Duplicates
    0.11
    _duplicates
    0.09
    Overlap
    0.09
    Equality
    0.08
    Duplicate
    0.08
    Intermediate
    0.08
     duplicates
    0.08
    duplicates
    0.08
     Иск
    0.07
    IGHTS
    0.07
    Act Density 0.023%

    No Known Activations