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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses symbols and their context in the text

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.83
    -0.74
    providedIn
    -0.73
    tagHelperRunner
    -0.72
     HasFactory
    -0.70
     Infórmanos
    -0.69
    TagMode
    -0.69
    SpringBootTest
    -0.69
     NSCoder
    -0.65
    GenerationType
    -0.65
    POSITIVE LOGITS
    The
    0.66
     the
    0.59
     The
    0.58
     A
    0.53
     
    0.49
     a
    0.46
     $
    0.44
    '
    0.44
     "
    0.43
     THE
    0.42
    Act Density 0.000%

    No Known Activations