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

    Neuronpedia

    INDEX
    Explanations

    terms related to testing and evaluation

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

    word endings and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.56
    writeFieldEnd
    -0.53
    jspx
    -0.45
    HasIndex
    -0.38
     pinulongan
    -0.38
    twimg
    -0.37
     <=",
    -0.37
    wapV
    -0.36
     Golden
    -0.35
    ༘
    -0.35
    POSITIVE LOGITS
    uxxxx
    1.25
    InjectAttribute
    0.88
    weightedMode
    0.63
    ValueStyle
    0.56
    WillAppear
    0.54
     MemoryStream
    0.54
    findpost
    0.53
     protoimpl
    0.53
    Rhestr
    0.52
    Autoritní
    0.52
    Act Density 0.013%

    No Known Activations