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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relationships and descriptions related to objects or concepts

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

    instances of examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✭✭
    -0.67
    دانشنامهٔ
    -0.62
     Roskov
    -0.60
     kasarigan
    -0.59
    :✨
    -0.56
    Хьажоргаш
    -0.53
     BoxFit
    -0.52
    fjspx
    -0.50
     purpoſe
    -0.50
    elemField
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.50
    findpost
    0.49
     například
    0.42
     notamment
    0.42
     addirittura
    0.37
     Spitze
    0.36
     tertentu
    0.36
     notably
    0.36
    czegó
    0.35
    特に
    0.35
    Act Density 0.075%

    No Known Activations