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

    Neuronpedia

    INDEX
    Explanations

    statements indicating the truth value of assertions or conditions

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

    Boolean "False" values

    np_acts-logits-general · gemini-2.0-flash

    detecting "False"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.65
    Cyfarwyddwr
    -0.61
    KURZBESCHREIBUNG
    -0.59
     referenties
    -0.59
    TagHelper
    -0.59
    lunda
    -0.55
     insuffisamment
    -0.55
    ADVANTAGES
    -0.54
    บ้าง
    -0.53
    ่านั้น
    -0.53
    POSITIVE LOGITS
     False
    0.84
    False
    0.79
     FALSE
    0.79
     false
    0.78
    false
    0.76
    FALSE
    0.72
     falsely
    0.61
    isTrue
    0.58
    bootstrapcdn
    0.53
    Autoritní
    0.52
    Act Density 0.108%

    No Known Activations