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

    Neuronpedia

    INDEX
    Explanations

    instructions and guidelines related to processes or actions

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

    followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    advice and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.65
    lapsingToolbar
    -0.63
    ScopeManager
    -0.61
    webElement
    -0.60
    存于互联网档案馆
    -0.59
     kaarangay
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    WriteTagHelper
    -0.57
    RTEE
    -0.56
    
    -0.55
    POSITIVE LOGITS
     lest
    0.78
     preferably
    0.67
    preferably
    0.61
     yoksa
    0.60
     jangan
    0.60
     helst
    0.60
     because
    0.57
    才行
    0.56
     чтобы
    0.56
     Otherwise
    0.53
    Act Density 0.473%

    No Known Activations