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

    Neuronpedia

    INDEX
    Explanations

    model's response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रक
    0.76
     obsah
    0.71
     trate
    0.63
    0.63
     Tập
    0.63
     Treatment
    0.62
    таль
    0.62
     континен
    0.61
     výkon
    0.61
     நிறைந்த
    0.61
    POSITIVE LOGITS
     whose
    0.82
     like
    0.81
    だけど
    0.75
     extrap
    0.74
    whose
    0.74
     තම
    0.72
     suggests
    0.71
     इंग्लिश
    0.70
     insinu
    0.69
     anagram
    0.69
    Act Density 0.098%

    No Known Activations