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

    Neuronpedia

    INDEX
    Explanations

    abbreviations, trace country origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rt
    0.52
    otypes
    0.48
    лефон
    0.47
    abies
    0.46
    itect
    0.45
     or
    0.45
    graphs
    0.45
     ধরনের
    0.44
    ported
    0.44
     natively
    0.43
    POSITIVE LOGITS
     prestataire
    0.47
     Most
    0.47
    Numer
    0.45
    нак
    0.45
     statut
    0.45
     அறி
    0.44
     Numer
    0.44
     Quantification
    0.44
     வாக
    0.44
     सेब
    0.44
    Act Density 0.002%

    No Known Activations