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

    Neuronpedia

    INDEX
    Explanations

    structures that indicate list items or categories

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

    markup and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.53
    uxxxx
    -0.50
    tagHelperRunner
    -0.49
     Autorizaciones
    -0.44
    LEncoder
    -0.43
    
    -0.42
    //
    -0.41
    balleur
    -0.41
    addGap
    -0.40
    neurial
    -0.40
    POSITIVE LOGITS
    mtd
    0.50
    RTLU
    0.48
    iço
    0.48
    AndEndTag
    0.47
    Personendaten
    0.46
    itemId
    0.46
    momix
    0.46
    item
    0.46
     argint
    0.45
    kemeja
    0.45
    Act Density 0.014%

    No Known Activations