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

    Neuronpedia

    INDEX
    Explanations

    list classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دشمن
    0.71
     दुश्मन
    0.64
    stan
    0.62
    rations
    0.60
    ftan
    0.59
    რ
    0.59
    started
    0.58
    typename
    0.58
    ከና
    0.58
    getR
    0.58
    POSITIVE LOGITS
     ours
    0.91
     مسلمانوں
    0.78
     Roosevelt
    0.74
     us
    0.72
     mele
    0.71
     conmigo
    0.70
     meille
    0.69
     भारता
    0.69
     Yankees
    0.69
     Lawn
    0.68
    Act Density 0.891%

    No Known Activations