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

    Neuronpedia

    INDEX
    Explanations

    encoding, complexity, distortion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гел
    0.42
     heer
    0.40
    ச்சே
    0.38
    жил
    0.38
     adresu
    0.37
     Hala
    0.36
    charAt
    0.36
     Schmidt
    0.36
    പ്പിച്ച
    0.36
     liberalization
    0.35
    POSITIVE LOGITS
    shortcuts
    0.44
     سيد
    0.39
     shortcuts
    0.38
     sitcom
    0.37
    Timeout
    0.36
     brightness
    0.36
     certainement
    0.35
    lymp
    0.35
     라고
    0.35
    蹺
    0.35
    Act Density 0.000%

    No Known Activations