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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<
    0.64
     susp
    0.53
    ig
    0.53
    াপন
    0.53
    POS
    0.50
     loosely
    0.49
    al
    0.49
     POS
    0.49
    ade
    0.49
     oss
    0.48
    POSITIVE LOGITS
    <unused244>
    0.84
    alaikums
    0.72
    <unused1769>
    0.71
     Daarnaast
    0.70
     berühm
    0.70
    <unused400>
    0.69
     स्यूशन
    0.68
    <unused387>
    0.68
    著名的
    0.68
    <unused1158>
    0.68
    Act Density 1.367%

    No Known Activations