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

    Neuronpedia

    INDEX
    Explanations

    elements related to enhancement or addition in context

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

    like "add" or "adds" and their variations

    np_acts-logits-general · gemini-2.0-flash

    adding or lending value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referrerpolicy
    -0.76
    RefNanny
    -0.69
    Manbalar
    -0.66
    JspWriter
    -0.63
     IBOutlet
    -0.63
    녕
    -0.61
     }}"></
    -0.59
    ]!=
    -0.59
    ьаж
    -0.58
    DebuggerNonUser
    -0.58
    POSITIVE LOGITS
     adds
    1.19
     added
    1.19
     adding
    1.17
    Adding
    1.09
     Adding
    1.08
     add
    1.08
     Adds
    1.06
    增添
    1.03
     Added
    1.02
    Added
    0.98
    Act Density 0.267%

    No Known Activations