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

    Neuronpedia

    INDEX
    Explanations

    terminology related to research, collaboration, and assistance in problem-solving

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

    helping with tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.59
    providedIn
    -0.46
    orianCalendar
    -0.44
    Халык
    -0.44
    inflate
    -0.43
    mappedBy
    -0.43
    SequentialGroup
    -0.42
    Revenir
    -0.41
    ſelf
    -0.40
     EXPEND
    -0.40
    POSITIVE LOGITS
     behulp
    0.54
    انيف
    0.53
     Helped
    0.53
     Grüsse
    0.50
     ajudar
    0.48
     aiut
    0.47
    помо
    0.47
     invokingState
    0.46
    aiuto
    0.46
     ayudar
    0.45
    Act Density 0.028%

    No Known Activations