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

    Neuronpedia

    INDEX
    Explanations

    references to authorship and documentation comments in code

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

    Preceding certain words (the, a, her)

    np_acts-logits-general · gemini-2.0-flash

    buy, online shopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.71
     pull
    -0.66
    raszam
    -0.64
    setVerticalGroup
    -0.63
     Monfieur
    -0.61
    scriptcase
    -0.60
     pulls
    -0.60
    PULL
    -0.59
    Pull
    -0.58
    mapStateToProps
    -0.58
    POSITIVE LOGITS
    </blockquote>
    0.61
    <eos>
    0.57
    "]').
    0.52
    "])
    0.51
    ']))
    0.48
    </h4>
    0.48
     дописавши
    0.48
     通販
    0.48
    ]()
    0.47
    ();*/
    0.47
    Act Density 0.026%

    No Known Activations