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

    Neuronpedia

    INDEX
    Explanations

    instances of confirmation or verification in relation to information or actions

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

    confirming information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FileOutputStream
    -0.32
    Language
    -0.31
    language
    -0.31
     Mors
    -0.31
     idea
    -0.31
    种
    -0.30
     House
    -0.30
    leben
    -0.30
    House
    -0.29
    Decoration
    -0.29
    POSITIVE LOGITS
     confirm
    1.02
     Confirm
    1.00
    confirm
    0.87
    Confirm
    0.85
     confirms
    0.79
     confirming
    0.78
    hoeddwyd
    0.77
     confirmer
    0.75
     الرياضيه
    0.75
     verify
    0.75
    Act Density 0.020%

    No Known Activations