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

    Neuronpedia

    INDEX
    Explanations

    statements related to significance and the importance of various concepts or experiences

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

    Followed by an infinitive ("to") or a comma

    np_acts-logits-general · gemini-2.0-flash

    importance and significance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.62
     ſta
    -0.58
    الحياه
    -0.57
     ModelExpression
    -0.56
     $_"
    -0.54
    ValueStyle
    -0.52
    :✨
    -0.52
     لينك
    -0.49
     ſte
    -0.49
    Gemeinden
    -0.49
    POSITIVE LOGITS
     very
    0.45
    OGND
    0.40
    .
    0.40
     dwind
    0.38
     unfortunately
    0.37
    AccessorTable
    0.36
     gyhoeddwyd
    0.36
     shown
    0.36
     extremely
    0.35
     Dyck
    0.35
    Act Density 1.249%

    No Known Activations