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

    Neuronpedia

    INDEX
    Explanations

    Java class and method definitions, particularly their structure and syntax

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

    Opening parenthesis, brackets, or tags

    np_acts-logits-general · gemini-2.0-flash

    numbers and ±

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.41
     Including
    -0.40
     fans
    -0.39
     bau
    -0.37
    kapital
    -0.37
    -"
    -0.37
    kamera
    -0.37
     But
    -0.37
     Instead
    -0.37
     Number
    -0.37
    POSITIVE LOGITS
    TagMode
    0.72
    endphp
    0.70
    MessageOf
    0.70
    ()]);
    0.67
    yntaxException
    0.67
    Portail
    0.66
     *)__
    0.65
    ErrUnexpectedEOF
    0.65
    }{*}{
    0.65
    sizeCache
    0.65
    Act Density 0.119%

    No Known Activations