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

    Neuronpedia

    INDEX
    Explanations

    novel and specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    0.40
    например
    0.39
    analysis
    0.39
    例えば
    0.39
    例如
    0.37
    over
    0.36
     например
    0.36
    hosting
    0.35
    resources
    0.35
    some
    0.35
    POSITIVE LOGITS
     bicycles
    0.50
     cookbooks
    0.49
     perros
    0.48
     bicycle
    0.48
     poultry
    0.48
     guitar
    0.47
     cookware
    0.46
    襪
    0.45
     guitars
    0.45
     haircuts
    0.43
    Act Density 0.016%

    No Known Activations