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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and reflections

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

    different comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.75
    setVerticalGroup
    -0.72
    ConstraintMaker
    -0.70
    KommentareTeilen
    -0.66
     ligiloj
    -0.63
     zwiſchen
    -0.63
     zuſammen
    -0.61
    期刊论文
    -0.61
     विश्वसनीयता
    -0.59
    contentLoaded
    -0.59
    POSITIVE LOGITS
    Personensuche
    0.32
     different
    0.32
    different
    0.29
     différente
    0.29
    PIN
    0.28
    moveToNext
    0.27
    /*
    0.27
     Bre
    0.26
    ish
    0.26
     différentes
    0.26
    Act Density 0.033%

    No Known Activations