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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to object-oriented programming and database entity definitions

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    programming code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.55
     chi
    -0.47
     con
    -0.46
    <eos>
    -0.46
     on
    -0.43
     no
    -0.43
    br
    -0.42
    足
    -0.42
    NOR
    -0.42
    ch
    -0.42
    POSITIVE LOGITS
    tvguidetime
    1.02
     autorytatywna
    0.98
     getBase
    0.97
     Shakspeare
    0.95
    ^(@)
    0.94
    تقاوى
    0.92
     itſelf
    0.92
     Efq
    0.92
     ligiloj
    0.89
     ProtoMessage
    0.89
    Act Density 0.186%

    No Known Activations