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

    Neuronpedia

    INDEX
    Explanations

    inquiries about knowledge and understanding in conversational contexts

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

    what happens and why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.58
    AndEndTag
    -0.47
    Diwedd
    -0.47
     createSprite
    -0.47
    ValueStyle
    -0.46
    sistors
    -0.45
    redient
    -0.45
    écnicas
    -0.45
    قایناق‌لار
    -0.43
    esomeness
    -0.43
    POSITIVE LOGITS
    JAXB
    0.44
     final
    0.38
    LookAnd
    0.35
    뀜
    0.34
    final
    0.34
    енча
    0.34
     brut
    0.34
     agenda
    0.33
     conformidad
    0.33
     consequ
    0.32
    Act Density 0.034%

    No Known Activations