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

    Neuronpedia

    INDEX
    Explanations

    phrases or constructs that denote a relative ranking or position

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

    extremity or superlative contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.77
    addContainerGap
    -0.67
    TagMode
    -0.66
     ProtoMessage
    -0.66
    \{\\
    -0.66
    ValueStyle
    -0.66
     للمعارف
    -0.63
     للاسماء
    -0.63
     вікісторінку
    -0.61
    AndEndTag
    -0.61
    POSITIVE LOGITS
    most
    1.20
     outermost
    0.93
     uppermost
    0.85
     innermost
    0.71
     most
    0.71
    MOST
    0.71
     farthest
    0.70
     foremost
    0.69
     furthest
    0.66
    Most
    0.62
    Act Density 0.014%

    No Known Activations