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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating satisfaction or approval

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

    with or at followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RuleContext
    -0.56
     تضيفلها
    -0.55
     <<<<<<<<<<<<<<
    -0.55
    exitRule
    -0.54
    uxxxx
    -0.50
    PageModule
    -0.49
    AutoScaleMode
    -0.49
     addItem
    -0.49
     CommonModule
    -0.48
     IFTT
    -0.48
    POSITIVE LOGITS
     the
    0.88
     how
    0.49
     this
    0.49
    the
    0.47
     what
    0.47
     its
    0.43
     their
    0.43
     ועל
    0.43
     את
    0.42
    aarrggbb
    0.42
    Act Density 0.012%

    No Known Activations