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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hasNext
    0.67
    cannot
    0.57
     breakage
    0.56
     timeouts
    0.51
     irreplaceable
    0.51
    earing
    0.50
    нным
    0.50
     cannot
    0.49
     involving
    0.49
     देंगे
    0.49
    POSITIVE LOGITS
     nice
    1.73
    Nice
    1.64
     Nice
    1.63
    nice
    1.61
     pleasure
    1.47
     prazer
    1.45
     Pleasure
    1.37
     glad
    1.29
     pleased
    1.27
     piacere
    1.25
    Act Density 0.035%

    No Known Activations