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

    Neuronpedia

    INDEX
    Explanations

    the end of a turn in a conversation or written dialogue

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

    royal figures and leadership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PyExc
    -0.54
     Signalez
    -0.52
    +#+#
    -0.52
    swick
    -0.51
    astify
    -0.47
    TagMode
    -0.47
    ⓧ
    -0.46
    Rujuakan
    -0.45
    íncia
    -0.45
    tagHelperRunner
    -0.45
    POSITIVE LOGITS
    EndProject
    0.44
    empereur
    0.43
     préféré
    0.42
    ValueGeneration
    0.39
     préf
    0.39
     çap
    0.38
    Empereur
    0.37
     supérieurs
    0.37
    deferred
    0.36
     disambiguazione
    0.36
    Act Density 0.072%

    No Known Activations