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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ția
    0.48
    ţia
    0.46
    তাহাদের
    0.44
    SXml
    0.42
     Ду
    0.41
     Waalaikumsalam
    0.41
    法施行令
    0.41
    əm
    0.41
    সজ্জিত
    0.41
    getStartState
    0.40
    POSITIVE LOGITS
     versions
    0.51
     breakdowns
    0.51
     businesses
    0.48
     linings
    0.47
     examples
    0.46
     🌱
    0.46
     😂
    0.46
     （
    0.46
     or
    0.45
     editions
    0.45
    Act Density 0.020%

    No Known Activations