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

    Neuronpedia

    INDEX
    Explanations

    brands and their products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক
    0.49
     Еще
    0.41
    น
    0.40
    ম
    0.39
     Analyzing
    0.39
     H
    0.38
    0.38
     A
    0.38
     democratization
    0.38
     laborers
    0.37
    POSITIVE LOGITS
    ens
    0.51
    shire
    0.49
    ifting
    0.47
    illiant
    0.47
    ${
    0.46
    age
    0.45
    icrous
    0.45
    å
    0.44
    ic
    0.44
    imde
    0.43
    Act Density 0.405%

    No Known Activations