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

    Neuronpedia

    INDEX
    Explanations

    single companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    囝
    1.29
     Ens
    1.27
    áil
    1.26
     Es
    1.22
     TT
    1.21
     family
    1.20
     Tw
    1.20
     readers
    1.19
     spelling
    1.19
     Testament
    1.18
    POSITIVE LOGITS
    7
    1.86
    8
    1.85
    9
    1.80
    6
    1.59
    0
    1.52
    Chill
    1.52
    4
    1.49
    5
    1.47
    3
    1.33
     инфра
    1.27
    Act Density 0.410%

    No Known Activations