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

    Neuronpedia

    INDEX
    Explanations

    essay prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     básicas
    -0.07
     throughout
    -0.07
     placeholders
    -0.07
     básicos
    -0.07
    'r
    -0.07
     fetch
    -0.07
     تج
    -0.07
    irms
    -0.07
    _com
    -0.07
     logic
    -0.07
    POSITIVE LOGITS
     sogenannte
    0.09
     Enum
    0.09
     шокол
    0.08
     Example
    0.08
     nämlich
    0.08
     näiteks
    0.08
     Enumer
    0.08
     Ég
    0.08
     yakni
    0.08
     म्हणजे
    0.08
    Act Density 0.112%

    No Known Activations