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

    Neuronpedia

    INDEX
    Explanations

    computer programming syntax related to dictionaries and data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    right/left parenthesis or angle bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.97
     Мексичка
    -0.94
    +#+#
    -0.92
     Roskov
    -0.91
     Efq
    -0.90
    ſelf
    -0.89
     myſelf
    -0.89
     Савезне
    -0.88
     المعيارى
    -0.85
    AndEndTag
    -0.85
    POSITIVE LOGITS
     
    0.50
     T
    0.44
     Ave
    0.44
      
    0.44
    ]
    0.42
     Apparently
    0.41
     Ver
    0.41
    ناسب
    0.41
     he
    0.40
    hofen
    0.40
    Act Density 1.001%

    No Known Activations