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

    Neuronpedia

    INDEX
    Explanations

    what you can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்துப்
    0.30
    éder
    0.27
    ASTIC
    0.25
    ARKS
    0.24
    вості
    0.24
    த்தைப்
    0.24
    Yb
    0.24
    atea
    0.24
    than
    0.24
    endroit
    0.24
    POSITIVE LOGITS
     этим
    0.26
     spawn
    0.25
     faixa
    0.25
     mockup
    0.24
     #
    0.24
     availability
    0.24
     ho
    0.24
     passo
    0.24
     engagements
    0.24
     remo
    0.23
    Act Density 0.002%

    No Known Activations