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

    Neuronpedia

    INDEX
    Explanations

    words indicating the existence of data or entities, particularly in past contexts

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

    past actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.57
     CommonModule
    -0.53
    ScopeManager
    -0.53
    Ƚ
    -0.52
    principalColumn
    -0.49
     AppCompatTheme
    -0.49
    rizona
    -0.48
    ddots
    -0.47
    verride
    -0.45
    irited
    -0.45
    POSITIVE LOGITS
     ddelweddau
    0.44
     صوتيه
    0.43
    devamını
    0.43
     مواليد
    0.43
     виправивши
    0.42
     createSprite
    0.41
     futures
    0.36
    تقاوى
    0.36
    ++)
    0.36
    AsUp
    0.35
    Act Density 0.154%

    No Known Activations