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

    Neuronpedia

    INDEX
    Explanations

    Active or relative paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    čnosti
    0.41
     উহার
    0.38
    निर्भर
    0.37
    ्यूम
    0.36
     behaving
    0.36
     Ereign
    0.35
     egiten
    0.35
    えます
    0.35
    ՝
    0.34
    heiten
    0.34
    POSITIVE LOGITS
    或者是
    0.62
    もしくは
    0.59
     maupun
    0.56
     или
    0.56
     or
    0.55
     hoặc
    0.54
    或是
    0.53
     ataupun
    0.52
     혹은
    0.49
     alebo
    0.49
    Act Density 0.283%

    No Known Activations