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

    Neuronpedia

    INDEX
    Explanations

    introduction or generative AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ără
    0.51
     рису
    0.48
    appeared
    0.46
     Cristal
    0.46
    த்தைத்
    0.46
     sfâr
    0.46
    ā
    0.45
     있으며
    0.45
    调
    0.44
    рисо
    0.44
    POSITIVE LOGITS
     cytokine
    0.51
     households
    0.49
     poaching
    0.48
     dagen
    0.47
     ព
    0.46
     genealog
    0.46
     value
    0.46
     geochemical
    0.46
     per
    0.46
     benthic
    0.45
    Act Density 0.010%

    No Known Activations