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

    Neuronpedia

    INDEX
    Explanations

    temporal concepts and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    0.55
    6
    0.53
    ៤
    0.51
    4
    0.51
    9
    0.47
    е
    0.44
    nament
    0.43
     維尼
    0.43
    5
    0.43
    7
    0.42
    POSITIVE LOGITS
     a
    0.47
     as
    0.46
     thơ
    0.45
     Acids
    0.44
     substances
    0.43
     Source
    0.43
     enzymes
    0.43
     Ах
    0.42
    欉
    0.42
     Molecules
    0.42
    Act Density 0.010%

    No Known Activations