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

    Neuronpedia

    INDEX
    Explanations

    terms and actions related to account management and logging processes

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

    control and state changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.50
    CodeAttribute
    -0.48
     initComponents
    -0.42
    tagext
    -0.41
    mobileqq
    -0.38
    клопе
    -0.38
    MessageState
    -0.38
     mergeFrom
    -0.38
     мѣ
    -0.36
     nhất
    -0.35
    POSITIVE LOGITS
     dezelve
    0.68
     zoude
    0.68
     hunne
    0.57
    genodigd
    0.57
     saurait
    0.57
     ainfi
    0.56
     illustrationer
    0.54
     zelve
    0.53
     zijne
    0.52
     latein
    0.52
    Act Density 0.030%

    No Known Activations