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

    Neuronpedia

    INDEX
    Explanations

    Dodgers, dogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +(
    0.42
    %(
    0.41
    ^(
    0.38
    ?(
    0.38
    |\
    0.38
    ^{
    0.38
    .(
    0.38
    ы
    0.38
    −
    0.38
    %.
    0.37
    POSITIVE LOGITS
     ক্লিক
    0.43
    filtered
    0.41
     movie
    0.40
     filtered
    0.40
     quanta
    0.40
     slid
    0.40
    试图
    0.40
    youtube
    0.39
     click
    0.39
     leftover
    0.39
    Act Density 0.004%

    No Known Activations