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

    Neuronpedia

    INDEX
    Explanations

    empty string literals

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

    code ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.54
    -------
    -0.52
     nonUne
    -0.50
    })),
    -0.49
    })));
    -0.48
    :].
    -0.48
    ]]:
    -0.47
    ுக்கு
    -0.47
     @{
    -0.47
     cui
    -0.46
    POSITIVE LOGITS
    BeginContext
    0.46
     piłkarz
    0.39
     prisonniers
    0.38
     prisão
    0.38
     ferdig
    0.36
    灵感
    0.36
     Italij
    0.35
     références
    0.35
     verrez
    0.35
    CodeAttribute
    0.35
    Act Density 0.012%

    No Known Activations