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

    Neuronpedia

    INDEX
    Explanations

    estimating proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ডা
    0.41
     Gin
    0.38
     consultative
    0.38
     signals
    0.38
    loops
    0.38
     lin
    0.38
    signals
    0.38
     Optical
    0.37
     Signals
    0.37
    ុ
    0.36
    POSITIVE LOGITS
    Hiking
    0.45
     Hiking
    0.40
    aży
    0.40
    偐
    0.39
     hiko
    0.38
    десят
    0.38
    bruck
    0.37
    Hint
    0.36
    зонта
    0.36
     Saddle
    0.36
    Act Density 0.001%

    No Known Activations