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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and data structures

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

    code context and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    -0.34
     ran
    -0.34
    $_
    -0.33
    -0.32
     Donaldson
    -0.32
    　　“
    -0.32
     
    -0.31
    -0.30
     do
    -0.30
    _
    -0.30
    POSITIVE LOGITS
    PerformLayout
    0.91
    QMetaType
    0.83
     חיצוניים
    0.75
     endforeach
    0.72
    <unused43>
    0.72
    ஥
    0.72
    <unused14>
    0.71
    <unused51>
    0.71
    [@BOS@]
    0.71
    <pad>
    0.71
    Act Density 0.245%

    No Known Activations